Georgakopoulous-soares and Parada et. al 2019

Non-B DNA structures across splice-sites

To investigate if non-B DNA structures can affect splicing, we explore the distribution of different motifs that are associated with Non-B DNA structures. We calculated the number of these motifs that can be found across splice sites (.num files) and then we calculated the positional enrichment of these across splice sites.

library(readr)
library(data.table)

package ‘data.table’ was built under R version 3.5.2data.table 1.12.8 using 2 threads (see ?getDTthreads).  Latest news: r-datatable.com

Attaching package: ‘data.table’

The following object is masked _by_ ‘.GlobalEnv’:

    .N

The following object is masked from ‘package:SummarizedExperiment’:

    shift

The following object is masked from ‘package:GenomicRanges’:

    shift

The following object is masked from ‘package:IRanges’:

    shift

The following objects are masked from ‘package:S4Vectors’:

    first, second

library(ggplot2)
library(plyr)

package ‘plyr’ was built under R version 3.5.2
Attaching package: ‘plyr’

The following object is masked from ‘package:matrixStats’:

    count

The following object is masked from ‘package:IRanges’:

    desc

The following object is masked from ‘package:S4Vectors’:

    rename

library(cowplot)

package ‘cowplot’ was built under R version 3.5.2
********************************************************
Note: As of version 1.0.0, cowplot does not change the
  default ggplot2 theme anymore. To recover the previous
  behavior, execute:
  theme_set(theme_cowplot())
********************************************************

library(Hmisc)

package ‘Hmisc’ was built under R version 3.5.2Loading required package: lattice
Loading required package: survival
package ‘survival’ was built under R version 3.5.2Loading required package: Formula

Attaching package: ‘Hmisc’

The following objects are masked from ‘package:plyr’:

    is.discrete, summarize

The following object is masked from ‘package:Biobase’:

    contents

The following objects are masked from ‘package:base’:

    format.pval, units

On this report we compile all the data analysis that lead us to get the final figures. For this, we processed several a

read_dist_table <- function(path){
  
dist_table <- data.table(read_delim(path, 
    "\t", escape_double = FALSE, col_names = FALSE, 
    trim_ws = TRUE))
dist_table <- dist_table[, 2:2001]
dist_table <- data.table(as.data.frame(t(dist_table)))
colnames(dist_table) <- c("Position", "Occurrences")
dist_table[,median:=median(Occurrences)]
dist_table[, Enrrichment:=Occurrences/median]
dist_table[, Position:=Position-1]
return(dist_table)  
}

plot_density <- function(up_plus, up_minus, down_plus, down_minus){
  
  up_TOTAL <-  merge(up_plus, up_minus, by="Position")
  up_TOTAL[,Occurrences:=Occurrences.x+Occurrences.y]
  up_TOTAL[,median:=median(Occurrences)]
  up_TOTAL[, Enrrichment:=Occurrences/median]
  up_TOTAL[, Position:=Position-1]
  
  
  down_TOTAL <-  merge(down_plus, down_minus, by="Position")
  down_TOTAL[,Occurrences:=Occurrences.x+Occurrences.y]
  down_TOTAL[,median:=median(Occurrences)]
  down_TOTAL[, Enrrichment:=Occurrences/median]
  down_TOTAL[, Position:=Position-1]
  
  up_TOTAL[ ,exon_pos:="Upstream"]
  down_TOTAL[ ,exon_pos:="Downstream"]
  
  TOTAL <- rbind(up_TOTAL, down_TOTAL)
  
  TOTAL$exon_pos <-  factor(TOTAL$exon_pos, levels=c("Upstream", "Downstream" )) 
  
  p <- ggplot(TOTAL)+
    geom_line(aes(x=Position,y=Enrrichment)) +
    facet_grid( . ~ exon_pos ) +
    theme_bw()
  
  show(p)
  
  TOTAL
  
  
}

plot_density_binomial <- function(up_plus, up_minus, down_plus, down_minus, observations, sig){
  
  up_TOTAL <-  merge(up_plus, up_minus, by="Position")
  up_TOTAL[,Occurrences:=Occurrences.x+Occurrences.y]
  up_TOTAL[,Occurrences:=Occurrences.x+Occurrences.y]
  
  
  
  up_TOTAL <- cbind(up_TOTAL, up_TOTAL[, binconf(Occurrences, observations, alpha=sig) ])
  up_TOTAL[,median:=median(PointEst)]
  up_TOTAL[, Enrrichment:=PointEst/median]
  up_TOTAL[, Enrrichment_l:=Lower/median]
  up_TOTAL[, Enrrichment_u:=Upper/median]
  up_TOTAL[, Position:=Position-1]
  
  
  down_TOTAL <-  merge(down_plus, down_minus, by="Position")
  down_TOTAL[,Occurrences:=Occurrences.x+Occurrences.y]
  
  down_TOTAL <- cbind(down_TOTAL, down_TOTAL[, binconf(Occurrences, observations, alpha=sig) ])
  down_TOTAL[,median:=median(PointEst)]
  down_TOTAL[, Enrrichment:=PointEst/median]
  down_TOTAL[, Enrrichment_l:=Lower/median]
  down_TOTAL[, Enrrichment_u:=Upper/median]
  down_TOTAL[, Position:=Position-1]  
  
  
  up_TOTAL[ ,exon_pos:="Upstream"]
  down_TOTAL[ ,exon_pos:="Downstream"]
  
  TOTAL <- rbind(up_TOTAL, down_TOTAL)
  
  TOTAL$exon_pos <-  factor(TOTAL$exon_pos, levels=c("Upstream", "Downstream" )) 
  
  p <- ggplot(TOTAL)+
    geom_line(aes(x=Position,y=Enrrichment)) +
    geom_ribbon(aes(ymin=Enrrichment_l, ymax=Enrrichment_u, x=Position), alpha=0.3 )+
    facet_grid( . ~ exon_pos ) +
    theme_bw()
  
  #show(p)
  
  return(TOTAL) 
  
}

G-Quadruplexes

G4.up_plus <- read_dist_table("./All_non_Bs/G4.exon.up_plus.list.out.num")
G4.down_plus <- read_dist_table("./All_non_Bs/G4.exon.down_plus.list.out.num")
G4.up_minus <- read_dist_table("./All_non_Bs/G4.exon.up_minus.list.out.num")
G4.down_minus <- read_dist_table("./All_non_Bs/G4.exon.down_minus.list.out.num")
G4.up_minus[,Position:=Position*-1]
G4.down_minus[,Position:=Position*-1]
G4.TOTAL <- plot_density(G4.up_plus, G4.up_minus, G4.down_plus, G4.down_minus) 

Directed repeats

DR.up_plus <- read_dist_table("./All_non_Bs/DR.exon.up_plus.list.out.num")
DR.down_plus <- read_dist_table("./All_non_Bs/DR.exon.down_plus.list.out.num")
DR.up_minus <- read_dist_table("./All_non_Bs/DR.exon.up_minus.list.out.num")
DR.down_minus <- read_dist_table("./All_non_Bs/DR.exon.down_minus.list.out.num")
DR.up_minus[,Position:=Position*-1]
DR.down_minus[,Position:=Position*-1]
DR.TOTAL <- plot_density(DR.up_plus, DR.up_minus, DR.down_plus, DR.down_minus)

H-DNA

H_DNA.up_plus <- read_dist_table("./All_non_Bs/H_DNA.exon.down_minus.list.out.num")
H_DNA.down_plus <- read_dist_table("./All_non_Bs/H_DNA.exon.down_plus.list.out.num")
H_DNA.up_minus <- read_dist_table("./All_non_Bs/H_DNA.exon.up_minus.list.out.num")
H_DNA.down_minus <- read_dist_table("./All_non_Bs/H_DNA.exon.down_minus.list.out.num")
H_DNA.up_minus[,Position:=Position*-1]
H_DNA.down_minus[,Position:=Position*-1]
H_DNA.TOTAL <- plot_density(H_DNA.up_plus, H_DNA.up_minus, H_DNA.down_plus, H_DNA.down_minus)

Inverted repeat

IR.up_plus <- read_dist_table("./All_non_Bs/IR.exon.down_minus.list.out.num")
IR.down_plus <- read_dist_table("./All_non_Bs/IR.exon.down_plus.list.out.num")
IR.up_minus <- read_dist_table("./All_non_Bs/IR.exon.up_minus.list.out.num")
IR.down_minus <- read_dist_table("./All_non_Bs/IR.exon.down_minus.list.out.num")
IR.up_minus[,Position:=Position*-1]
IR.down_minus[,Position:=Position*-1]
IR.TOTAL <- plot_density(IR.up_plus, IR.up_minus, IR.down_plus, IR.down_minus)

Mirror repeat

MR.up_plus <- read_dist_table("./All_non_Bs/MR.exon.down_minus.list.out.num")
MR.down_plus <- read_dist_table("./All_non_Bs/MR.exon.down_plus.list.out.num")
MR.up_minus <- read_dist_table("./All_non_Bs/MR.exon.up_minus.list.out.num")
MR.down_minus <- read_dist_table("./All_non_Bs/MR.exon.down_minus.list.out.num")
MR.up_minus[,Position:=Position*-1]
MR.down_minus[,Position:=Position*-1]
MR.TOTAL <- plot_density(MR.up_plus, MR.up_minus, MR.down_plus, MR.down_minus)

Short tandem repeat

STR.up_plus <- read_dist_table("./All_non_Bs/STR.exon.down_minus.list.out.num")
STR.down_plus <- read_dist_table("./All_non_Bs/STR.exon.down_plus.list.out.num")
STR.up_minus <- read_dist_table("./All_non_Bs/STR.exon.up_minus.list.out.num")
STR.down_minus <- read_dist_table("./All_non_Bs/STR.exon.down_minus.list.out.num")
STR.up_minus[,Position:=Position*-1]
STR.down_minus[,Position:=Position*-1]
STR.TOTAL <- plot_density(STR.up_plus, STR.up_minus, STR.down_plus, STR.down_minus)

Z-DNA

Z_DNA.up_plus <- read_dist_table("./All_non_Bs/Z_DNA.exon.down_minus.list.out.num")
Z_DNA.down_plus <- read_dist_table("./All_non_Bs/Z_DNA.exon.down_plus.list.out.num")
Z_DNA.up_minus <- read_dist_table("./All_non_Bs/Z_DNA.exon.up_minus.list.out.num")
Z_DNA.down_minus <- read_dist_table("./All_non_Bs/Z_DNA.exon.down_minus.list.out.num")
Z_DNA.up_minus[,Position:=Position*-1]
Z_DNA.down_minus[,Position:=Position*-1]
Z_DNA.TOTAL <- plot_density(Z_DNA.up_plus, Z_DNA.up_minus, Z_DNA.down_plus, Z_DNA.down_minus)

All Non-B DNA motifs

G4.TOTAL[, Non_B:="G4"]
DR.TOTAL[, Non_B:="DR"]
H_DNA.TOTAL[, Non_B:="H DNA"]
IR.TOTAL[, Non_B:="IR"]
MR.TOTAL[, Non_B:="MR"]
STR.TOTAL[, Non_B:="STR"]
Z_DNA.TOTAL[, Non_B:="Z DNA"]
Non_B.TOTAL <- rbind(G4.TOTAL, DR.TOTAL, H_DNA.TOTAL, IR.TOTAL, MR.TOTAL, STR.TOTAL, Z_DNA.TOTAL)
Fig1.A <- ggplot(Non_B.TOTAL)+
    geom_line(aes(x=Position,y=Enrrichment)) +
    xlim(c(-300,300)) +
    facet_grid( Non_B ~ exon_pos ) +
  theme_bw()
Fig1.A

Non_B.TOTAL.Enrrichment_Peak <- Non_B.TOTAL[ , .(Enrrichment_Peak=max(Enrrichment)) , by = c("Non_B", "exon_pos" )]
write.table(Non_B.TOTAL.Enrrichment_Peak, file = "./Tables/Non_B.TOTAL.Enrrichment_Peak.txt", append = FALSE, quote = FALSE, sep = "\t",
            eol = "\n", na = "NA", dec = ".", row.names = FALSE,
            col.names = TRUE, qmethod = c("escape", "double"),
            fileEncoding = "")

Distribution of non-B DNA motifs across weak and strong splice sites

We calculated the distribution of non-B DNA motifs across quartiles of splice strength, where Q1 are the weakest splice sites and Q4 are the strongest.

Merge_Qs <- function(Qs.list, window_len, strand ) {
  
  Total_Qs <- data.table(rbindlist(Qs.list))
  Q_names <- seq(nrow(Total_Qs)/window_len)
  Total_Qs[, Q:=rep(Q_names, each=window_len)]
  
  if(strand=="-"){
    
    Total_Qs[,Position:=Position*-1]
  }
  
  Total_Qs
}

merge_plus_minus <- function(plus, minus){
  TOTAL <- merge(plus, minus, by=c("Position", "Q") )
  TOTAL[,Occurrences:=Occurrences.x+Occurrences.y]
  TOTAL[,median:=median(Occurrences),  by=c("Q")]
  TOTAL[, Enrrichment:=Occurrences/median]
  TOTAL[, Position:=Position-1]
  
}

Merge_up_down <- function(Qs.up, Qs.down){
  Qs.total <- rbind(Qs.up, Qs.down)
  
  half_n <- nrow(Qs.total)/2
  Qs.total[, exon_pos:=rep(c("Upstream", "Downstream"), each=half_n) ]
  
  
  Qs.total$exon_pos <-  factor(Qs.total$exon_pos, levels=c("Upstream", "Downstream" ))
  Qs.total$Q <-  factor(Qs.total$Q)
  
  Qs.total
  
}

get_total_Qs <- function(Qs.plus.up.list, Qs.minus.list, Qs.plus.down.list, Qs.minus.down.list, window_len){
  Qs.plus.up <- Merge_Qs(Qs.plus.up.list, window_len, strand="+")
  Qs.minus.up <- Merge_Qs(Qs.minus.list, window_len, strand="-")
  Qs.up <- merge_plus_minus(Qs.plus.up, Qs.minus.up)
  
  Qs.plus.down <- Merge_Qs(Qs.plus.down.list, window_len, strand="+")
  Qs.minus.down<- Merge_Qs(Qs.minus.down.list, window_len, strand="-")
  Qs.down <- merge_plus_minus(Qs.plus.down, Qs.minus.down)
  
  Qs.total <- Merge_up_down(Qs.up, Qs.down)
  
  Qs.total
  
}
  

G4.Q1_up_plus <- read_dist_table("./All_non_Bs/q1_q4/exon.up_plus.q1.bed.G4.list.out.num")

Parsed with column specification:
cols(
  .default = col_double()
)
See spec(...) for full column specifications.
1 parsing failure.
row col     expected       actual                                                     file
  2  -- 2001 columns 2002 columns './All_non_Bs/q1_q4/exon.up_plus.q1.bed.G4.list.out.num'

G4.Q2_up_plus <- read_dist_table("./All_non_Bs/q1_q4/exon.up_plus.q2.bed.G4.list.out.num")

Parsed with column specification:
cols(
  .default = col_double()
)
See spec(...) for full column specifications.
1 parsing failure.
row col     expected       actual                                                     file
  2  -- 2001 columns 2002 columns './All_non_Bs/q1_q4/exon.up_plus.q2.bed.G4.list.out.num'

G4.Q3_up_plus <- read_dist_table("./All_non_Bs/q1_q4/exon.up_plus.q3.bed.G4.list.out.num")

Parsed with column specification:
cols(
  .default = col_double()
)
See spec(...) for full column specifications.
1 parsing failure.
row col     expected       actual                                                     file
  2  -- 2001 columns 2002 columns './All_non_Bs/q1_q4/exon.up_plus.q3.bed.G4.list.out.num'

G4.Q4_up_plus <- read_dist_table("./All_non_Bs/q1_q4/exon.up_plus.q4.bed.G4.list.out.num")

Parsed with column specification:
cols(
  .default = col_double()
)
See spec(...) for full column specifications.
1 parsing failure.
row col     expected       actual                                                     file
  2  -- 2001 columns 2002 columns './All_non_Bs/q1_q4/exon.up_plus.q4.bed.G4.list.out.num'

G4.Q1_down_plus <- read_dist_table("./All_non_Bs/q1_q4/exon.down_plus.q1.bed.G4.list.out.num")

Parsed with column specification:
cols(
  .default = col_double()
)
See spec(...) for full column specifications.
1 parsing failure.
row col     expected       actual                                                       file
  2  -- 2001 columns 2002 columns './All_non_Bs/q1_q4/exon.down_plus.q1.bed.G4.list.out.num'

G4.Q2_down_plus <- read_dist_table("./All_non_Bs/q1_q4/exon.down_plus.q2.bed.G4.list.out.num")

Parsed with column specification:
cols(
  .default = col_double()
)
See spec(...) for full column specifications.
1 parsing failure.
row col     expected       actual                                                       file
  2  -- 2001 columns 2002 columns './All_non_Bs/q1_q4/exon.down_plus.q2.bed.G4.list.out.num'

G4.Q3_down_plus <- read_dist_table("./All_non_Bs/q1_q4/exon.down_plus.q3.bed.G4.list.out.num")

Parsed with column specification:
cols(
  .default = col_double()
)
See spec(...) for full column specifications.
1 parsing failure.
row col     expected       actual                                                       file
  2  -- 2001 columns 2002 columns './All_non_Bs/q1_q4/exon.down_plus.q3.bed.G4.list.out.num'

G4.Q4_down_plus <- read_dist_table("./All_non_Bs/q1_q4/exon.down_plus.q4.bed.G4.list.out.num")

Parsed with column specification:
cols(
  .default = col_double()
)
See spec(...) for full column specifications.
1 parsing failure.
row col     expected       actual                                                       file
  2  -- 2001 columns 2002 columns './All_non_Bs/q1_q4/exon.down_plus.q4.bed.G4.list.out.num'

G4.Q1_up_minus <- read_dist_table("./All_non_Bs/q1_q4/exon.up_minus.q1.bed.G4.list.out.num")

Parsed with column specification:
cols(
  .default = col_double()
)
See spec(...) for full column specifications.
1 parsing failure.
row col     expected       actual                                                      file
  2  -- 2001 columns 2002 columns './All_non_Bs/q1_q4/exon.up_minus.q1.bed.G4.list.out.num'

G4.Q2_up_minus <- read_dist_table("./All_non_Bs/q1_q4/exon.up_minus.q2.bed.G4.list.out.num")

Parsed with column specification:
cols(
  .default = col_double()
)
See spec(...) for full column specifications.
1 parsing failure.
row col     expected       actual                                                      file
  2  -- 2001 columns 2002 columns './All_non_Bs/q1_q4/exon.up_minus.q2.bed.G4.list.out.num'

G4.Q3_up_minus <- read_dist_table("./All_non_Bs/q1_q4/exon.up_minus.q3.bed.G4.list.out.num")

Parsed with column specification:
cols(
  .default = col_double()
)
See spec(...) for full column specifications.
1 parsing failure.
row col     expected       actual                                                      file
  2  -- 2001 columns 2002 columns './All_non_Bs/q1_q4/exon.up_minus.q3.bed.G4.list.out.num'

G4.Q4_up_minus <- read_dist_table("./All_non_Bs/q1_q4/exon.up_minus.q4.bed.G4.list.out.num")

Parsed with column specification:
cols(
  .default = col_double()
)
See spec(...) for full column specifications.
1 parsing failure.
row col     expected       actual                                                      file
  2  -- 2001 columns 2002 columns './All_non_Bs/q1_q4/exon.up_minus.q4.bed.G4.list.out.num'

G4.Q1_down_minus <- read_dist_table("./All_non_Bs/q1_q4/exon.down_minus.q1.bed.G4.list.out.num")

Parsed with column specification:
cols(
  .default = col_double()
)
See spec(...) for full column specifications.
1 parsing failure.
row col     expected       actual                                                        file
  2  -- 2001 columns 2002 columns './All_non_Bs/q1_q4/exon.down_minus.q1.bed.G4.list.out.num'

G4.Q2_down_minus <- read_dist_table("./All_non_Bs/q1_q4/exon.down_minus.q2.bed.G4.list.out.num")

Parsed with column specification:
cols(
  .default = col_double()
)
See spec(...) for full column specifications.
1 parsing failure.
row col     expected       actual                                                        file
  2  -- 2001 columns 2002 columns './All_non_Bs/q1_q4/exon.down_minus.q2.bed.G4.list.out.num'

G4.Q3_down_minus <- read_dist_table("./All_non_Bs/q1_q4/exon.down_minus.q3.bed.G4.list.out.num")

Parsed with column specification:
cols(
  .default = col_double()
)
See spec(...) for full column specifications.
1 parsing failure.
row col     expected       actual                                                        file
  2  -- 2001 columns 2002 columns './All_non_Bs/q1_q4/exon.down_minus.q3.bed.G4.list.out.num'

G4.Q4_down_minus <- read_dist_table(".//All_non_Bs/q1_q4/exon.down_minus.q4.bed.G4.list.out.num")

Parsed with column specification:
cols(
  .default = col_double()
)
See spec(...) for full column specifications.
1 parsing failure.
row col     expected       actual                                                         file
  2  -- 2001 columns 2002 columns './/All_non_Bs/q1_q4/exon.down_minus.q4.bed.G4.list.out.num'

G4.Qs.plus.up.list <- list(G4.Q1_up_plus, G4.Q2_up_plus, G4.Q3_up_plus, G4.Q4_up_plus)
G4.Qs.minus.list <- list(G4.Q1_up_minus, G4.Q2_up_minus, G4.Q3_up_minus, G4.Q4_up_minus)
G4.Qs.plus.down.list <- list(G4.Q1_down_plus, G4.Q2_down_plus, G4.Q3_down_plus, G4.Q4_down_plus)
G4.Qs.minus.down.list <- list(G4.Q1_down_minus, G4.Q2_down_minus, G4.Q3_down_minus, G4.Q4_down_minus)
G4.window_len = 2000
G4.Qs.total <- get_total_Qs(G4.Qs.plus.up.list, G4.Qs.minus.list, G4.Qs.plus.down.list, G4.Qs.minus.down.list, G4.window_len)
G4.Qs.total$Q <- mapvalues(G4.Qs.total$Q,  from =c(1:4), to =c("Q1", "Q2", "Q3", "Q4"))
ggplot(G4.Qs.total)+
  geom_line(aes(x=Position,y=Enrrichment, colour=Q)) +
  xlim(c(-150,150)) +
  facet_grid( . ~ exon_pos ) +
  theme(text = element_text(size=15)) +
  theme_bw()+labs(colour = "Splice site stregth quartile") +
   theme(legend.position = "top", legend.direction = "horizontal")

We calculated the binomial confidence intervals given the total number of exon in each quartile

hg19.nexons <- 123433 + 123936  #Number of exons found in each side
G4.Qs.total.binomial <- cbind(G4.Qs.total,  G4.Qs.total[, binconf(Occurrences, hg19.nexons/4) ])
G4.Qs.total.binomial[ , median:=median(PointEst), by=c("exon_pos", "Q")]
G4.Qs.total.binomial[, `:=`(Enrrichment=PointEst/median, Enrrichment_l=Lower/median, Enrrichment_u=Upper/median)]
ggplot(G4.Qs.total.binomial)+
  geom_line(aes(x=Position,y=Enrrichment, colour=Q)) +
  geom_ribbon(aes(x=Position,y=Enrrichment, fill=Q, ymin=Enrrichment_l, ymax=Enrrichment_u), alpha=0.3) +
  xlim(c(-150,150)) +
  facet_grid( . ~ exon_pos ) +
  theme(text = element_text(size=15)) +
  theme_bw()+labs(colour = "Splice site stregth quartile") +
   theme(legend.position = "top", legend.direction = "horizontal")

Then we explored the enrichment in other non-B DNA motifs

DR.Q1_up_plus <- read_dist_table("./All_non_Bs/q1_q4/exon.up_plus.q1.bed.DRs.list.out.num")
DR.Q2_up_plus <- read_dist_table("./All_non_Bs/q1_q4/exon.up_plus.q2.bed.DRs.list.out.num")
DR.Q3_up_plus <- read_dist_table("./All_non_Bs/q1_q4/exon.up_plus.q3.bed.DRs.list.out.num")
DR.Q4_up_plus <- read_dist_table("./All_non_Bs/q1_q4/exon.up_plus.q4.bed.DRs.list.out.num")
DR.Q1_down_plus <- read_dist_table("./All_non_Bs/q1_q4/exon.down_plus.q1.bed.DRs.list.out.num")
DR.Q2_down_plus <- read_dist_table("./All_non_Bs/q1_q4/exon.down_plus.q2.bed.DRs.list.out.num")
DR.Q3_down_plus <- read_dist_table("./All_non_Bs/q1_q4/exon.down_plus.q3.bed.DRs.list.out.num")
DR.Q4_down_plus <- read_dist_table("./All_non_Bs/q1_q4/exon.down_plus.q4.bed.DRs.list.out.num")
DR.Q1_up_minus <- read_dist_table("./All_non_Bs/q1_q4/exon.up_minus.q1.bed.DRs.list.out.num")
DR.Q2_up_minus <- read_dist_table("./All_non_Bs/q1_q4/exon.up_minus.q2.bed.DRs.list.out.num")
DR.Q3_up_minus <- read_dist_table("./All_non_Bs/q1_q4/exon.up_minus.q3.bed.DRs.list.out.num")
DR.Q4_up_minus <- read_dist_table("./All_non_Bs/q1_q4/exon.up_minus.q4.bed.DRs.list.out.num")
DR.Q1_down_minus <- read_dist_table("./All_non_Bs/q1_q4/exon.down_minus.q1.bed.DRs.list.out.num")
DR.Q2_down_minus <- read_dist_table("./All_non_Bs/q1_q4/exon.down_minus.q2.bed.DRs.list.out.num")
DR.Q3_down_minus <- read_dist_table("./All_non_Bs/q1_q4/exon.down_minus.q3.bed.DRs.list.out.num")
DR.Q4_down_minus <- read_dist_table("./All_non_Bs/q1_q4/exon.down_minus.q4.bed.DRs.list.out.num")
DR.Qs.plus.up.list <- list(DR.Q1_up_plus, DR.Q2_up_plus, DR.Q3_up_plus, DR.Q4_up_plus)
DR.Qs.minus.list <- list(DR.Q1_up_minus, DR.Q2_up_minus, DR.Q3_up_minus, DR.Q4_up_minus)
DR.Qs.plus.down.list <- list(DR.Q1_down_plus, DR.Q2_down_plus, DR.Q3_down_plus, DR.Q4_down_plus)
DR.Qs.minus.down.list <- list(DR.Q1_down_minus, DR.Q2_down_minus, DR.Q3_down_minus, DR.Q4_down_minus)
DR.window_len = 2000
DR.Qs.total <- get_total_Qs(DR.Qs.plus.up.list, DR.Qs.minus.list, DR.Qs.plus.down.list, DR.Qs.minus.down.list, DR.window_len)
  

H_DNA.Q1_up_plus <- read_dist_table("./All_non_Bs/q1_q4/exon.up_plus.q1.bed.H_DNA.list.out.num")
H_DNA.Q2_up_plus <- read_dist_table("./All_non_Bs/q1_q4/exon.up_plus.q2.bed.H_DNA.list.out.num")
H_DNA.Q3_up_plus <- read_dist_table("./All_non_Bs/q1_q4/exon.up_plus.q3.bed.H_DNA.list.out.num")
H_DNA.Q4_up_plus <- read_dist_table("./All_non_Bs/q1_q4/exon.up_plus.q4.bed.H_DNA.list.out.num")
H_DNA.Q1_down_plus <- read_dist_table("./All_non_Bs/q1_q4/exon.down_plus.q1.bed.H_DNA.list.out.num")
H_DNA.Q2_down_plus <- read_dist_table("./All_non_Bs/q1_q4/exon.down_plus.q2.bed.H_DNA.list.out.num")
H_DNA.Q3_down_plus <- read_dist_table("./All_non_Bs/q1_q4/exon.down_plus.q3.bed.H_DNA.list.out.num")
H_DNA.Q4_down_plus <- read_dist_table("./All_non_Bs/q1_q4/exon.down_plus.q4.bed.H_DNA.list.out.num")
H_DNA.Q1_up_minus <- read_dist_table("./All_non_Bs/q1_q4/exon.up_minus.q1.bed.H_DNA.list.out.num")
H_DNA.Q2_up_minus <- read_dist_table("./All_non_Bs/q1_q4/exon.up_minus.q2.bed.H_DNA.list.out.num")
H_DNA.Q3_up_minus <- read_dist_table("./All_non_Bs/q1_q4/exon.up_minus.q3.bed.H_DNA.list.out.num")
H_DNA.Q4_up_minus <- read_dist_table("./All_non_Bs/q1_q4/exon.up_minus.q4.bed.H_DNA.list.out.num")
H_DNA.Q1_down_minus <- read_dist_table("./All_non_Bs/q1_q4/exon.down_minus.q1.bed.H_DNA.list.out.num")
H_DNA.Q2_down_minus <- read_dist_table("./All_non_Bs/q1_q4/exon.down_minus.q2.bed.H_DNA.list.out.num")
H_DNA.Q3_down_minus <- read_dist_table("./All_non_Bs/q1_q4/exon.down_minus.q3.bed.H_DNA.list.out.num")
H_DNA.Q4_down_minus <- read_dist_table("./All_non_Bs/q1_q4/exon.down_minus.q4.bed.H_DNA.list.out.num")
H_DNA.Qs.plus.up.list <- list(H_DNA.Q1_up_plus, H_DNA.Q2_up_plus, H_DNA.Q3_up_plus, H_DNA.Q4_up_plus)
H_DNA.Qs.minus.list <- list(H_DNA.Q1_up_minus, H_DNA.Q2_up_minus, H_DNA.Q3_up_minus, H_DNA.Q4_up_minus)
H_DNA.Qs.plus.down.list <- list(H_DNA.Q1_down_plus, H_DNA.Q2_down_plus, H_DNA.Q3_down_plus, H_DNA.Q4_down_plus)
H_DNA.Qs.minus.down.list <- list(H_DNA.Q1_down_minus, H_DNA.Q2_down_minus, H_DNA.Q3_down_minus, H_DNA.Q4_down_minus)
H_DNA.window_len = 2000
H_DNA.Qs.total <- get_total_Qs(H_DNA.Qs.plus.up.list, H_DNA.Qs.minus.list, H_DNA.Qs.plus.down.list, H_DNA.Qs.minus.down.list, H_DNA.window_len)

IR.Q1_up_plus <- read_dist_table("./All_non_Bs/q1_q4/exon.up_plus.q1.bed.IRs.list.out.num")
IR.Q2_up_plus <- read_dist_table("./All_non_Bs/q1_q4/exon.up_plus.q2.bed.IRs.list.out.num")
IR.Q3_up_plus <- read_dist_table("./All_non_Bs/q1_q4/exon.up_plus.q3.bed.IRs.list.out.num")
IR.Q4_up_plus <- read_dist_table("./All_non_Bs/q1_q4/exon.up_plus.q4.bed.IRs.list.out.num")
IR.Q1_down_plus <- read_dist_table("./All_non_Bs/q1_q4/exon.down_plus.q1.bed.IRs.list.out.num")
IR.Q2_down_plus <- read_dist_table("./All_non_Bs/q1_q4/exon.down_plus.q2.bed.IRs.list.out.num")
IR.Q3_down_plus <- read_dist_table("./All_non_Bs/q1_q4/exon.down_plus.q3.bed.IRs.list.out.num")
IR.Q4_down_plus <- read_dist_table("./All_non_Bs/q1_q4/exon.down_plus.q4.bed.IRs.list.out.num")
IR.Q1_up_minus <- read_dist_table("./All_non_Bs/q1_q4/exon.up_minus.q1.bed.IRs.list.out.num")
IR.Q2_up_minus <- read_dist_table("./All_non_Bs/q1_q4/exon.up_minus.q2.bed.IRs.list.out.num")
IR.Q3_up_minus <- read_dist_table("./All_non_Bs/q1_q4/exon.up_minus.q3.bed.IRs.list.out.num")
IR.Q4_up_minus <- read_dist_table("./All_non_Bs/q1_q4/exon.up_minus.q4.bed.IRs.list.out.num")
IR.Q1_down_minus <- read_dist_table("./All_non_Bs/q1_q4/exon.down_minus.q1.bed.IRs.list.out.num")
IR.Q2_down_minus <- read_dist_table("./All_non_Bs/q1_q4/exon.down_minus.q2.bed.IRs.list.out.num")
IR.Q3_down_minus <- read_dist_table("./All_non_Bs/q1_q4/exon.down_minus.q3.bed.IRs.list.out.num")
IR.Q4_down_minus <- read_dist_table("./All_non_Bs/q1_q4/exon.down_minus.q4.bed.IRs.list.out.num")
IR.Qs.plus.up.list <- list(IR.Q1_up_plus, IR.Q2_up_plus, IR.Q3_up_plus, IR.Q4_up_plus)
IR.Qs.minus.list <- list(IR.Q1_up_minus, IR.Q2_up_minus, IR.Q3_up_minus, IR.Q4_up_minus)
IR.Qs.plus.down.list <- list(IR.Q1_down_plus, IR.Q2_down_plus, IR.Q3_down_plus, IR.Q4_down_plus)
IR.Qs.minus.down.list <- list(IR.Q1_down_minus, IR.Q2_down_minus, IR.Q3_down_minus, IR.Q4_down_minus)
IR.window_len = 2000
IR.Qs.total <- get_total_Qs(IR.Qs.plus.up.list, IR.Qs.minus.list, IR.Qs.plus.down.list, IR.Qs.minus.down.list, IR.window_len)

MR.Q1_up_plus <- read_dist_table("./All_non_Bs/q1_q4/exon.up_plus.q1.bed.MRs.list.out.num")
MR.Q2_up_plus <- read_dist_table("./All_non_Bs/q1_q4/exon.up_plus.q2.bed.MRs.list.out.num")
MR.Q3_up_plus <- read_dist_table("./All_non_Bs/q1_q4/exon.up_plus.q3.bed.MRs.list.out.num")
MR.Q4_up_plus <- read_dist_table("./All_non_Bs/q1_q4/exon.up_plus.q4.bed.MRs.list.out.num")
MR.Q1_down_plus <- read_dist_table("./All_non_Bs/q1_q4/exon.down_plus.q1.bed.MRs.list.out.num")
MR.Q2_down_plus <- read_dist_table("./All_non_Bs/q1_q4/exon.down_plus.q2.bed.MRs.list.out.num")
MR.Q3_down_plus <- read_dist_table("./All_non_Bs/q1_q4/exon.down_plus.q3.bed.MRs.list.out.num")
MR.Q4_down_plus <- read_dist_table("./All_non_Bs/q1_q4/exon.down_plus.q4.bed.MRs.list.out.num")
MR.Q1_up_minus <- read_dist_table("./All_non_Bs/q1_q4/exon.up_minus.q1.bed.MRs.list.out.num")
MR.Q2_up_minus <- read_dist_table("./All_non_Bs/q1_q4/exon.up_minus.q2.bed.MRs.list.out.num")
MR.Q3_up_minus <- read_dist_table("./All_non_Bs/q1_q4/exon.up_minus.q3.bed.MRs.list.out.num")
MR.Q4_up_minus <- read_dist_table("./All_non_Bs/q1_q4/exon.up_minus.q4.bed.MRs.list.out.num")
MR.Q1_down_minus <- read_dist_table("./All_non_Bs/q1_q4/exon.down_minus.q1.bed.MRs.list.out.num")
MR.Q2_down_minus <- read_dist_table("./All_non_Bs/q1_q4/exon.down_minus.q2.bed.MRs.list.out.num")
MR.Q3_down_minus <- read_dist_table("./All_non_Bs/q1_q4/exon.down_minus.q3.bed.MRs.list.out.num")
MR.Q4_down_minus <- read_dist_table("./All_non_Bs/q1_q4/exon.down_minus.q4.bed.MRs.list.out.num")
MR.Qs.plus.up.list <- list(MR.Q1_up_plus, MR.Q2_up_plus, MR.Q3_up_plus, MR.Q4_up_plus)
MR.Qs.minus.list <- list(MR.Q1_up_minus, MR.Q2_up_minus, MR.Q3_up_minus, MR.Q4_up_minus)
MR.Qs.plus.down.list <- list(MR.Q1_down_plus, MR.Q2_down_plus, MR.Q3_down_plus, MR.Q4_down_plus)
MR.Qs.minus.down.list <- list(MR.Q1_down_minus, MR.Q2_down_minus, MR.Q3_down_minus, MR.Q4_down_minus)
MR.window_len = 2000
MR.Qs.total <- get_total_Qs(MR.Qs.plus.up.list, MR.Qs.minus.list, MR.Qs.plus.down.list, MR.Qs.minus.down.list, MR.window_len)

STR.Q1_up_plus <- read_dist_table("./All_non_Bs/q1_q4/exon.up_plus.q1.bed.STRs.list.out.num")
STR.Q2_up_plus <- read_dist_table("./All_non_Bs/q1_q4/exon.up_plus.q2.bed.STRs.list.out.num")
STR.Q3_up_plus <- read_dist_table("./All_non_Bs/q1_q4/exon.up_plus.q3.bed.STRs.list.out.num")
STR.Q4_up_plus <- read_dist_table("./All_non_Bs/q1_q4/exon.up_plus.q4.bed.STRs.list.out.num")
STR.Q1_down_plus <- read_dist_table("./All_non_Bs/q1_q4/exon.down_plus.q1.bed.STRs.list.out.num")
STR.Q2_down_plus <- read_dist_table("./All_non_Bs/q1_q4/exon.down_plus.q2.bed.STRs.list.out.num")
STR.Q3_down_plus <- read_dist_table("./All_non_Bs/q1_q4/exon.down_plus.q3.bed.STRs.list.out.num")
STR.Q4_down_plus <- read_dist_table("./All_non_Bs/q1_q4/exon.down_plus.q4.bed.STRs.list.out.num")
STR.Q1_up_minus <- read_dist_table("./All_non_Bs/q1_q4/exon.up_minus.q1.bed.STRs.list.out.num")
STR.Q2_up_minus <- read_dist_table("./All_non_Bs/q1_q4/exon.up_minus.q2.bed.STRs.list.out.num")
STR.Q3_up_minus <- read_dist_table("./All_non_Bs/q1_q4/exon.up_minus.q3.bed.STRs.list.out.num")
STR.Q4_up_minus <- read_dist_table("./All_non_Bs/q1_q4/exon.up_minus.q4.bed.STRs.list.out.num")
STR.Q1_down_minus <- read_dist_table("./All_non_Bs/q1_q4/exon.down_minus.q1.bed.STRs.list.out.num")
STR.Q2_down_minus <- read_dist_table("./All_non_Bs/q1_q4/exon.down_minus.q2.bed.STRs.list.out.num")
STR.Q3_down_minus <- read_dist_table("./All_non_Bs/q1_q4/exon.down_minus.q3.bed.STRs.list.out.num")
STR.Q4_down_minus <- read_dist_table("./All_non_Bs/q1_q4/exon.down_minus.q4.bed.STRs.list.out.num")
STR.Qs.plus.up.list <- list(STR.Q1_up_plus, STR.Q2_up_plus, STR.Q3_up_plus, STR.Q4_up_plus)
STR.Qs.minus.list <- list(STR.Q1_up_minus, STR.Q2_up_minus, STR.Q3_up_minus, STR.Q4_up_minus)
STR.Qs.plus.down.list <- list(STR.Q1_down_plus, STR.Q2_down_plus, STR.Q3_down_plus, STR.Q4_down_plus)
STR.Qs.minus.down.list <- list(STR.Q1_down_minus, STR.Q2_down_minus, STR.Q3_down_minus, STR.Q4_down_minus)
STR.window_len = 2000
STR.Qs.total <- get_total_Qs(STR.Qs.plus.up.list, STR.Qs.minus.list, STR.Qs.plus.down.list, STR.Qs.minus.down.list, STR.window_len)

Z_DNA.Q1_up_plus <- read_dist_table("./All_non_Bs/q1_q4/exon.up_plus.q1.bed.Z_DNA.list.out.num")
Z_DNA.Q2_up_plus <- read_dist_table("./All_non_Bs/q1_q4/exon.up_plus.q2.bed.Z_DNA.list.out.num")
Z_DNA.Q3_up_plus <- read_dist_table("./All_non_Bs/q1_q4/exon.up_plus.q3.bed.Z_DNA.list.out.num")
Z_DNA.Q4_up_plus <- read_dist_table("./All_non_Bs/q1_q4/exon.up_plus.q4.bed.Z_DNA.list.out.num")
Z_DNA.Q1_down_plus <- read_dist_table("./All_non_Bs/q1_q4/exon.down_plus.q1.bed.Z_DNA.list.out.num")
Z_DNA.Q2_down_plus <- read_dist_table("./All_non_Bs/q1_q4/exon.down_plus.q2.bed.Z_DNA.list.out.num")
Z_DNA.Q3_down_plus <- read_dist_table("./All_non_Bs/q1_q4/exon.down_plus.q3.bed.Z_DNA.list.out.num")
Z_DNA.Q4_down_plus <- read_dist_table("./All_non_Bs/q1_q4/exon.down_plus.q4.bed.Z_DNA.list.out.num")
Z_DNA.Q1_up_minus <- read_dist_table("./All_non_Bs/q1_q4/exon.up_minus.q1.bed.Z_DNA.list.out.num")
Z_DNA.Q2_up_minus <- read_dist_table("./All_non_Bs/q1_q4/exon.up_minus.q2.bed.Z_DNA.list.out.num")
Z_DNA.Q3_up_minus <- read_dist_table("./All_non_Bs/q1_q4/exon.up_minus.q3.bed.Z_DNA.list.out.num")
Z_DNA.Q4_up_minus <- read_dist_table("./All_non_Bs/q1_q4/exon.up_minus.q4.bed.Z_DNA.list.out.num")
Z_DNA.Q1_down_minus <- read_dist_table("./All_non_Bs/q1_q4/exon.down_minus.q1.bed.Z_DNA.list.out.num")
Z_DNA.Q2_down_minus <- read_dist_table("./All_non_Bs/q1_q4/exon.down_minus.q2.bed.Z_DNA.list.out.num")
Z_DNA.Q3_down_minus <- read_dist_table("./All_non_Bs/q1_q4/exon.down_minus.q3.bed.Z_DNA.list.out.num")
Z_DNA.Q4_down_minus <- read_dist_table("./All_non_Bs/q1_q4/exon.down_minus.q4.bed.Z_DNA.list.out.num")
Z_DNA.Qs.plus.up.list <- list(Z_DNA.Q1_up_plus, Z_DNA.Q2_up_plus, Z_DNA.Q3_up_plus, Z_DNA.Q4_up_plus)
Z_DNA.Qs.minus.list <- list(Z_DNA.Q1_up_minus, Z_DNA.Q2_up_minus, Z_DNA.Q3_up_minus, Z_DNA.Q4_up_minus)
Z_DNA.Qs.plus.down.list <- list(Z_DNA.Q1_down_plus, Z_DNA.Q2_down_plus, Z_DNA.Q3_down_plus, Z_DNA.Q4_down_plus)
Z_DNA.Qs.minus.down.list <- list(Z_DNA.Q1_down_minus, Z_DNA.Q2_down_minus, Z_DNA.Q3_down_minus, Z_DNA.Q4_down_minus)
Z_DNA.window_len = 2000
Z_DNA.Qs.total <- get_total_Qs(Z_DNA.Qs.plus.up.list, Z_DNA.Qs.minus.list, Z_DNA.Qs.plus.down.list, Z_DNA.Qs.minus.down.list, Z_DNA.window_len)

G4.Qs.total[, Non_B:="G4"]
DR.Qs.total[, Non_B:="DR"]
H_DNA.Qs.total[, Non_B:="H-DNA"]
IR.Qs.total[, Non_B:="IR"]
MR.Qs.total[, Non_B:="MR"]
STR.Qs.total[, Non_B:="STR"]
Z_DNA.Qs.total[, Non_B:="Z-DNA"]
Non_B.Qs.TOTAL <- rbind(G4.Qs.total, DR.Qs.total, H_DNA.Qs.total, IR.Qs.total, MR.Qs.total, STR.Qs.total, Z_DNA.Qs.total)
Non_B.Qs.TOTAL$Q <- mapvalues(Non_B.Qs.TOTAL$Q,  from =c(1:4), to =c("Q1", "Q2", "Q3", "Q4"))
ggplot(Non_B.Qs.TOTAL)+
  geom_line(aes(x=Position,y=Enrrichment, colour=Q)) +
  xlim(c(-150,150)) +
  facet_grid( Non_B ~ exon_pos ) +
  labs(colour = "Splice site stregth quartile") +
  theme_bw()  + 
  theme(legend.position = "top", legend.direction = "horizontal")

Non_B.Qs.TOTAL.Enrrichment_Peak <- Non_B.Qs.TOTAL[  , .(Enrrichment_Peak=max(Enrrichment)) , by= c("Non_B", "exon_pos", "Q")]
write.table(Non_B.Qs.TOTAL.Enrrichment_Peak, file = "./Tables/Non_B.Qs.TOTAL.Enrrichment_Peak.txt", append = FALSE, quote = FALSE, sep = "\t",
            eol = "\n", na = "NA", dec = ".", row.names = FALSE,
            col.names = TRUE, qmethod = c("escape", "double"),
            fileEncoding = "")

Template - non template

To investigate if the distribution of non-B DNA motifs is biased by transcription direction, we generate .num files where the counts were separated by template and non templated strands:

• Template = plus_minus, minus_plus
• Non-template = minus_minus, plus_plus

G4.template.Q1_up_plus <- read_dist_table("./template_non_template/exon.up_plus.q1.bed.G4s_minus_plus.list.final.num")
G4.template.Q2_up_plus <- read_dist_table("./template_non_template/exon.up_plus.q2.bed.G4s_minus_plus.list.final.num")
G4.template.Q3_up_plus <- read_dist_table("./template_non_template/exon.up_plus.q3.bed.G4s_minus_plus.list.final.num")
G4.template.Q4_up_plus <- read_dist_table("./template_non_template/exon.up_plus.q4.bed.G4s_minus_plus.list.final.num")
G4.template.Q1_up_minus <- read_dist_table("./template_non_template/exon.up_minus.q1.bed.G4s_plus_minus.list.final.num")
G4.template.Q2_up_minus <- read_dist_table("./template_non_template/exon.up_minus.q2.bed.G4s_plus_minus.list.final.num")
G4.template.Q3_up_minus <- read_dist_table("./template_non_template/exon.up_minus.q3.bed.G4s_plus_minus.list.final.num")
G4.template.Q4_up_minus <- read_dist_table("./template_non_template/exon.up_minus.q4.bed.G4s_plus_minus.list.final.num")
G4.template.Q1_down_plus <- read_dist_table("./template_non_template/exon.down_plus.q1.bed.G4s_minus_plus.list.final.num")
G4.template.Q2_down_plus <- read_dist_table("./template_non_template/exon.down_plus.q2.bed.G4s_minus_plus.list.final.num")
G4.template.Q3_down_plus <- read_dist_table("./template_non_template/exon.down_plus.q3.bed.G4s_minus_plus.list.final.num")
G4.template.Q4_down_plus <- read_dist_table("./template_non_template/exon.down_plus.q4.bed.G4s_minus_plus.list.final.num")
G4.template.Q1_down_minus <- read_dist_table("./template_non_template/exon.down_minus.q1.bed.G4s_plus_minus.list.final.num")
G4.template.Q2_down_minus <- read_dist_table("./template_non_template/exon.down_minus.q2.bed.G4s_plus_minus.list.final.num")
G4.template.Q3_down_minus <- read_dist_table("./template_non_template/exon.down_minus.q3.bed.G4s_plus_minus.list.final.num")
G4.template.Q4_down_minus <- read_dist_table("./template_non_template/exon.down_minus.q4.bed.G4s_plus_minus.list.final.num")
G4.non_template.Q1_up_plus <- read_dist_table("./template_non_template/exon.up_plus.q1.bed.G4s_plus_plus.list.final.num")
G4.non_template.Q2_up_plus <- read_dist_table("./template_non_template/exon.up_plus.q2.bed.G4s_plus_plus.list.final.num")
G4.non_template.Q3_up_plus <- read_dist_table("./template_non_template/exon.up_plus.q3.bed.G4s_plus_plus.list.final.num")
G4.non_template.Q4_up_plus <- read_dist_table("./template_non_template/exon.up_plus.q4.bed.G4s_plus_plus.list.final.num")
G4.non_template.Q1_up_minus <- read_dist_table("./template_non_template/exon.up_minus.q1.bed.G4s_minus_minus.list.final.num")
G4.non_template.Q2_up_minus <- read_dist_table("./template_non_template/exon.up_minus.q2.bed.G4s_minus_minus.list.final.num")
G4.non_template.Q3_up_minus <- read_dist_table("./template_non_template/exon.up_minus.q3.bed.G4s_minus_minus.list.final.num")
G4.non_template.Q4_up_minus <- read_dist_table("./template_non_template/exon.up_minus.q4.bed.G4s_minus_minus.list.final.num")
G4.non_template.Q1_down_plus <- read_dist_table("./template_non_template/exon.down_plus.q1.bed.G4s_plus_plus.list.final.num")
G4.non_template.Q2_down_plus <- read_dist_table("./template_non_template/exon.down_plus.q2.bed.G4s_plus_plus.list.final.num")
G4.non_template.Q3_down_plus <- read_dist_table("./template_non_template/exon.down_plus.q3.bed.G4s_plus_plus.list.final.num")
G4.non_template.Q4_down_plus <- read_dist_table("./template_non_template/exon.down_plus.q4.bed.G4s_plus_plus.list.final.num")
G4.non_template.Q1_down_minus <- read_dist_table("./template_non_template/exon.down_minus.q1.bed.G4s_minus_minus.list.final.num")
G4.non_template.Q2_down_minus <- read_dist_table("./template_non_template/exon.down_minus.q2.bed.G4s_minus_minus.list.final.num")
G4.non_template.Q3_down_minus <- read_dist_table("./template_non_template/exon.down_minus.q3.bed.G4s_minus_minus.list.final.num")
G4.non_template.Q4_down_minus <- read_dist_table("./template_non_template/exon.down_minus.q4.bed.G4s_minus_minus.list.final.num")

G4.template.Qs.plus.up.list <- list(G4.template.Q1_up_plus, G4.template.Q2_up_plus, G4.template.Q3_up_plus, G4.template.Q4_up_plus)
G4.template.Qs.minus.list <- list(G4.template.Q1_up_minus, G4.template.Q2_up_minus, G4.template.Q3_up_minus, G4.template.Q4_up_minus)
G4.template.Qs.plus.down.list <- list(G4.template.Q1_down_plus, G4.template.Q2_down_plus, G4.template.Q3_down_plus, G4.template.Q4_down_plus)
G4.template.Qs.minus.down.list <- list(G4.template.Q1_down_minus, G4.template.Q2_down_minus, G4.template.Q3_down_minus, G4.template.Q4_down_minus)
G4.template.window_len = 2000
G4.template.Qs.total <- get_total_Qs(G4.template.Qs.plus.up.list, G4.template.Qs.minus.list, G4.template.Qs.plus.down.list, G4.template.Qs.minus.down.list, G4.template.window_len)

G4.non_template.Qs.plus.up.list <- list(G4.non_template.Q1_up_plus, G4.non_template.Q2_up_plus, G4.non_template.Q3_up_plus, G4.non_template.Q4_up_plus)
G4.non_template.Qs.minus.list <- list(G4.non_template.Q1_up_minus, G4.non_template.Q2_up_minus, G4.non_template.Q3_up_minus, G4.non_template.Q4_up_minus)
G4.non_template.Qs.plus.down.list <- list(G4.non_template.Q1_down_plus, G4.non_template.Q2_down_plus, G4.non_template.Q3_down_plus, G4.non_template.Q4_down_plus)
G4.non_template.Qs.minus.down.list <- list(G4.non_template.Q1_down_minus, G4.non_template.Q2_down_minus, G4.non_template.Q3_down_minus, G4.non_template.Q4_down_minus)
G4.non_template.window_len = 2000
G4.non_template.Qs.total <- get_total_Qs(G4.non_template.Qs.plus.up.list, G4.non_template.Qs.minus.list, G4.non_template.Qs.plus.down.list, G4.non_template.Qs.minus.down.list, G4.template.window_len)

G4.template.Qs.total

       Position Q Occurrences.x median.x Enrrichment.x Occurrences.y median.y Enrrichment.y Occurrences median Enrrichment   exon_pos
    1:    -1000 1           147      179     0.8212291           152      175     0.8685714         299    351   0.8518519   Upstream
    2:    -1000 2           126      134     0.9402985           141      135     1.0444444         267    268   0.9962687   Upstream
    3:    -1000 3           100       99     1.0101010            94       94     1.0000000         194    192   1.0104167   Upstream
    4:    -1000 4            63       66     0.9545455            74       65     1.1384615         137    131   1.0458015   Upstream
    5:     -999 1           149      179     0.8324022           150      175     0.8571429         299    351   0.8518519   Upstream
   ---                                                                                                                               
15988:      997 4            99      108     0.9166667           104      104     1.0000000         203    211   0.9620853 Downstream
15989:      998 1           119      137     0.8686131           111      129     0.8604651         230    266   0.8646617 Downstream
15990:      998 2           109      128     0.8515625           117      127     0.9212598         226    252   0.8968254 Downstream
15991:      998 3           106      110     0.9636364           109      109     1.0000000         215    217   0.9907834 Downstream
15992:      998 4            96      108     0.8888889           104      104     1.0000000         200    211   0.9478673 Downstream

G4.non_template.Qs.total

       Position Q Occurrences.x median.x Enrrichment.x Occurrences.y median.y Enrrichment.y Occurrences median Enrrichment   exon_pos
    1:    -1000 1           193      202     0.9554455           174      200     0.8700000         367    406   0.9039409   Upstream
    2:    -1000 2           148      161     0.9192547           120      149     0.8053691         268    309   0.8673139   Upstream
    3:    -1000 3           124      122     1.0163934           113      108     1.0462963         237    229   1.0349345   Upstream
    4:    -1000 4            84       74     1.1351351            70       70     1.0000000         154    144   1.0694444   Upstream
    5:     -999 1           193      202     0.9554455           177      200     0.8850000         370    406   0.9113300   Upstream
   ---                                                                                                                               
15988:      997 4           102      114     0.8947368            99      109     0.9082569         201    225   0.8933333 Downstream
15989:      998 1           123      154     0.7987013           128      136     0.9411765         251    289   0.8685121 Downstream
15990:      998 2           128      147     0.8707483           114      139     0.8201439         242    288   0.8402778 Downstream
15991:      998 3           108      125     0.8640000            90      122     0.7377049         198    249   0.7951807 Downstream
15992:      998 4            98      114     0.8596491            99      109     0.9082569         197    225   0.8755556 Downstream

G4.template_non_template.Qs.total <- rbind(G4.template.Qs.total, G4.non_template.Qs.total)
  
half_n <- nrow(G4.template_non_template.Qs.total)/2
G4.template_non_template.Qs.total[, Strand:=rep(c("Template", "Non-template"), each=half_n) ]
  
  
  
  
G4.template_non_template.Qs.total$Strand <-  factor(G4.template_non_template.Qs.total$Strand, levels=c("Template", "Non-template" ))
  

G4.template_non_template.Qs.total$Q <- mapvalues(G4.template_non_template.Qs.total$Q,  from =c(1:4), to =c("Q1", "Q2", "Q3", "Q4"))
G4.template_non_template.Qs.total.binomial <- cbind(G4.template_non_template.Qs.total,  G4.template_non_template.Qs.total[, binconf(Occurrences, hg19.nexons/8) ])
G4.template_non_template.Qs.total.binomial[, median:=NULL]
G4.template_non_template.Qs.total.binomial[ , median:=median(PointEst), by=c("exon_pos", "Q", "Strand")]
G4.template_non_template.Qs.total.binomial[, `:=`(Enrrichment=PointEst/median, Enrrichment_l=Lower/median, Enrrichment_u=Upper/median)]
Fig2.A <- ggplot(G4.template_non_template.Qs.total.binomial)+
  geom_line(aes(x=Position,y=Enrrichment, colour=Q)) +
   geom_ribbon(aes(x=Position, fill=Q, ymin=Enrrichment_l, ymax=Enrrichment_u), alpha=0.3) +
  xlim(c(-150,150)) +
  facet_grid( Strand ~ exon_pos ) +
  labs(colour = "Splice site stregth quartile") +
  theme_bw()  + 
  theme(legend.position = "top", legend.direction = "horizontal")
Fig2.A

G4.template_non_template.total <- G4.template_non_template.Qs.total[ , .(Occurrences=sum(Occurrences)) , by=c("Strand", "exon_pos", "Position")]
G4.template_non_template.total[ , median:=median(Occurrences) , by=c("Strand", "exon_pos")]
G4.template_non_template.total[ , Enrrichment:=Occurrences/median , by=c("Strand", "exon_pos", "Position")]
ggplot(G4.template_non_template.total)+
  geom_line(aes(x=Position,y=Enrrichment)) +
  xlim(c(-150,150)) +
  facet_grid( Strand ~ exon_pos ) +
  labs(colour = "Splice site stregth quartile") +
  theme_bw()  + 
  theme(legend.position = "top", legend.direction = "horizontal")

G4.template_non_template.total_Peak <- G4.template_non_template.total[  , .(Enrrichment_Peak=max(Enrrichment)) , by= c("Strand", "exon_pos")]
write.table(G4.template_non_template.total_Peak, file = "./Tables/G4.template_non_template.total_Peak.txt", append = FALSE, quote = FALSE, sep = "\t",
            eol = "\n", na = "NA", dec = ".", row.names = FALSE,
            col.names = TRUE, qmethod = c("escape", "double"),
            fileEncoding = "")

G4.template_non_template.Qs.total.Enrrichment_Peak <- G4.template_non_template.Qs.total[  , .(Enrrichment_Peak=max(Enrrichment)) , by= c( "exon_pos", "Q", "Strand" )]
write.table(G4.template_non_template.Qs.total.Enrrichment_Peak, file = "./Tables/G4.template_non_template.Qs.total.Enrrichment_Peak.txt", append = FALSE, quote = FALSE, sep = "\t",
            eol = "\n", na = "NA", dec = ".", row.names = FALSE,
            col.names = TRUE, qmethod = c("escape", "double"),
            fileEncoding = "")

G4 RUNS

Here we explored the enrichment of G-quadruplexes with different G-run length

G1_up_plus <- read_dist_table("./G4_runs/exon.up_plus.bed.Single_G_runs.list.out.num")
G2_up_plus <- read_dist_table("./G4_runs/exon.up_plus.bed.Twice_G_runs.list.out.num")
G3_up_plus <- read_dist_table("./G4_runs/exon.up_plus.bed.Three_G_runs.list.out.num")
G4_up_plus <- read_dist_table("./G4_runs/exon.up_plus.bed.Four_G_runs.list.out.num")
G5_up_plus <- read_dist_table("./G4_runs/exon.up_plus.bed.Five_G_runs.list.out.num")
G6_up_plus <- read_dist_table("./G4_runs/exon.up_plus.bed.Six_G_runs.list.out.num")
G1_up_minus <- read_dist_table("./G4_runs/exon.up_minus.bed.Single_G_runs.list.out.num")
G2_up_minus <- read_dist_table("./G4_runs/exon.up_minus.bed.Twice_G_runs.list.out.num")
G3_up_minus <- read_dist_table("./G4_runs/exon.up_minus.bed.Three_G_runs.list.out.num")
G4_up_minus <- read_dist_table("./G4_runs/exon.up_minus.bed.Four_G_runs.list.out.num")
G5_up_minus <- read_dist_table("./G4_runs/exon.up_minus.bed.Five_G_runs.list.out.num")
G6_up_minus <- read_dist_table("./G4_runs/exon.up_minus.bed.Six_G_runs.list.out.num")
G1_down_plus <- read_dist_table("./G4_runs/exon.down_plus.bed.Single_G_runs.list.out.num")
G2_down_plus <- read_dist_table("./G4_runs/exon.down_plus.bed.Twice_G_runs.list.out.num")
G3_down_plus <- read_dist_table("./G4_runs/exon.down_plus.bed.Three_G_runs.list.out.num")
G4_down_plus <- read_dist_table("./G4_runs/exon.down_plus.bed.Four_G_runs.list.out.num")
G5_down_plus <- read_dist_table("./G4_runs/exon.down_plus.bed.Five_G_runs.list.out.num")
G6_down_plus <- read_dist_table("./G4_runs/exon.down_plus.bed.Six_G_runs.list.out.num")
G1_down_minus <- read_dist_table("./G4_runs/exon.down_minus.bed.Single_G_runs.list.out.num")
G2_down_minus <- read_dist_table("./G4_runs/exon.down_minus.bed.Twice_G_runs.list.out.num")
G3_down_minus <- read_dist_table("./G4_runs/exon.down_minus.bed.Three_G_runs.list.out.num")
G4_down_minus <- read_dist_table("./G4_runs/exon.down_minus.bed.Four_G_runs.list.out.num")  
G5_down_minus <- read_dist_table("./G4_runs/exon.down_minus.bed.Five_G_runs.list.out.num")
G6_down_minus <- read_dist_table("./G4_runs/exon.down_minus.bed.Six_G_runs.list.out.num")

Gruns.up_plus.list <- list(G1_up_plus, G2_up_plus, G3_up_plus, G4_up_plus, G5_up_plus, G6_up_plus)
Gruns.up_minus.list <- list(G1_up_minus, G2_up_minus, G3_up_minus, G4_up_minus, G5_up_minus, G6_up_minus)
Gruns.down_plus.list <- list(G1_down_plus, G2_down_plus, G3_down_plus, G4_down_plus, G5_down_plus, G6_down_plus)
Gruns.down_minus.list <- list(G1_down_minus, G2_down_minus, G3_down_minus, G4_down_minus, G5_down_minus, G6_down_minus)
Gruns.window_len = 2000
Gruns.total <- get_total_Qs(Gruns.up_plus.list, Gruns.up_minus.list, Gruns.down_plus.list, Gruns.down_minus.list, Gruns.window_len)
Gruns.total[, G_run_length:=Q]

Gruns.total.binomial <- cbind(Gruns.total,  Gruns.total[, binconf(Occurrences, hg19.nexons) ])
Gruns.total.binomial[, median:=NULL]
Gruns.total.binomial[ , median:=median(PointEst), by=c("exon_pos", "Q" )]
Gruns.total.binomial[, `:=`(Enrrichment=PointEst/median, Enrrichment_l=Lower/median, Enrrichment_u=Upper/median)]
Fig2.B <- ggplot(Gruns.total.binomial)+
  geom_line(aes(x=Position,y=Enrrichment, colour=G_run_length)) +
  geom_ribbon(aes(x=Position, fill=Q, ymin=Enrrichment_l, ymax=Enrrichment_u), alpha=0.3) +
  xlim(c(-100,100)) +
  facet_grid( . ~ exon_pos ) +
  theme(text = element_text(size=15)) +
  theme_bw() +
  labs(colour = "Number of consecutive G-runs") +
  theme(legend.position = "top", legend.direction = "horizontal")
Fig2.B

Gruns.total.Enrrichment_Peak <- Gruns.total[  , .(Enrrichment_Peak=max(Enrrichment)) , by= c( "exon_pos", "G_run_length")]
write.table(Gruns.total.Enrrichment_Peak, file = "./Tables/Gruns.total.Enrrichment_Peak.txt", append = FALSE, quote = FALSE, sep = "\t",
            eol = "\n", na = "NA", dec = ".", row.names = FALSE,
            col.names = TRUE, qmethod = c("escape", "double"),
            fileEncoding = "")

G4 enrichment across evolution

We analyzed the G4 enrichment across splice sites from different species

susScr11.up_plus <- read_dist_table("./Evolution/susScr11.exon.up_plus.bed.score.susScr11.txt..list.out.num")
susScr11.down_plus <- read_dist_table("./Evolution/susScr11.exon.down_plus.bed.score.susScr11.txt..list.out.num")
susScr11.up_minus <- read_dist_table("./Evolution/susScr11.exon.up_minus.bed.score.susScr11.txt..list.out.num")
susScr11.down_minus <- read_dist_table("./Evolution/susScr11.exon.down_minus.bed.score.susScr11.txt..list.out.num")
susScr11.up_minus[,Position:=Position*-1]
susScr11.down_minus[,Position:=Position*-1]
susScr11.TOTAL <- plot_density(susScr11.up_plus, susScr11.up_minus, susScr11.down_plus, susScr11.down_minus)

TAIR10.up_plus <- read_dist_table("./Evolution/TAIR10.exon.up_plus.bed.score.TAIR10.txt..list.out.num")
TAIR10.down_plus <- read_dist_table("./Evolution/TAIR10.exon.down_plus.bed.score.TAIR10.txt..list.out.num")
TAIR10.up_minus <- read_dist_table("./Evolution/TAIR10.exon.up_minus.bed.score.TAIR10.txt..list.out.num")
TAIR10.down_minus <- read_dist_table("./Evolution/TAIR10.exon.down_minus.bed.score.TAIR10.txt..list.out.num")
TAIR10.up_minus[,Position:=Position*-1]
TAIR10.down_minus[,Position:=Position*-1]
TAIR10.TOTAL <- plot_density(TAIR10.up_plus, TAIR10.up_minus, TAIR10.down_plus, TAIR10.down_minus)

anoCar2.up_plus <- read_dist_table("./Evolution/anoCar2.exon.up_plus.bed.score.anoCar2.txt..list.out.num")
anoCar2.down_plus <- read_dist_table("./Evolution/anoCar2.exon.down_plus.bed.score.anoCar2.txt..list.out.num")
anoCar2.up_minus <- read_dist_table("./Evolution/anoCar2.exon.up_minus.bed.score.anoCar2.txt..list.out.num")
anoCar2.down_minus <- read_dist_table("./Evolution/anoCar2.exon.down_minus.bed.score.anoCar2.txt..list.out.num")
anoCar2.up_minus[,Position:=Position*-1]
anoCar2.down_minus[,Position:=Position*-1]
anoCar2.TOTAL <- plot_density(anoCar2.up_plus, anoCar2.up_minus, anoCar2.down_plus, anoCar2.down_minus)

xenTro9.up_plus <- read_dist_table("./Evolution/xenTro9.exon.up_plus.bed.score.xenTro9.txt..list.out.num")
xenTro9.down_plus <- read_dist_table("./Evolution/xenTro9.exon.down_plus.bed.score.xenTro9.txt..list.out.num")
xenTro9.up_minus <- read_dist_table("./Evolution/xenTro9.exon.up_minus.bed.score.xenTro9.txt..list.out.num")
xenTro9.down_minus <- read_dist_table("./Evolution/xenTro9.exon.down_minus.bed.score.xenTro9.txt..list.out.num")
xenTro9.up_minus[,Position:=Position*-1]
xenTro9.down_minus[,Position:=Position*-1]
xenTro9.TOTAL <- plot_density(xenTro9.up_plus, xenTro9.up_minus, xenTro9.down_plus, xenTro9.down_minus)

ce10.up_plus <- read_dist_table("./Evolution/ce10.exon.up_plus.bed.score.ce10.txt..list.out.num")
ce10.down_plus <- read_dist_table("./Evolution/ce10.exon.down_plus.bed.score.ce10.txt..list.out.num")
ce10.up_minus <- read_dist_table("./Evolution/ce10.exon.up_minus.bed.score.ce10.txt..list.out.num")
ce10.down_minus <- read_dist_table("./Evolution/ce10.exon.down_minus.bed.score.ce10.txt..list.out.num")
ce10.up_minus[,Position:=Position*-1]
ce10.down_minus[,Position:=Position*-1]
ce10.TOTAL <- plot_density(ce10.up_plus, ce10.up_minus, ce10.down_plus, ce10.down_minus)

danRer11.up_plus <- read_dist_table("./Evolution/danRer11.exon.up_plus.bed.score.danRer11.txt..list.out.num")
danRer11.down_plus <- read_dist_table("./Evolution/danRer11.exon.down_plus.bed.score.danRer11.txt..list.out.num")
danRer11.up_minus <- read_dist_table("./Evolution/danRer11.exon.up_minus.bed.score.danRer11.txt..list.out.num")
danRer11.down_minus <- read_dist_table("./Evolution/danRer11.exon.down_minus.bed.score.danRer11.txt..list.out.num")
danRer11.up_minus[,Position:=Position*-1]
danRer11.down_minus[,Position:=Position*-1]
danRer11.TOTAL <- plot_density(danRer11.up_plus, danRer11.up_minus, danRer11.down_plus, danRer11.down_minus)

mm10.up_plus <- read_dist_table("./Evolution/mm10.exon.up_plus.bed.score.mm10.txt..list.out.num")
mm10.down_plus <- read_dist_table("./Evolution/mm10.exon.down_plus.bed.score.mm10.txt..list.out.num")
mm10.up_minus <- read_dist_table("./Evolution/mm10.exon.up_minus.bed.score.mm10.txt..list.out.num")
mm10.down_minus <- read_dist_table("./Evolution/mm10.exon.down_minus.bed.score.mm10.txt..list.out.num")
mm10.up_minus[,Position:=Position*-1]
mm10.down_minus[,Position:=Position*-1]
mm10.TOTAL <- plot_density(mm10.up_plus, mm10.up_minus, mm10.down_plus, mm10.down_minus)

hg19.up_plus <- read_dist_table("./Evolution/hg19.exon.up_plus.bed.score.hg19.txt..list.out.num")
hg19.down_plus <- read_dist_table("./Evolution/hg19.exon.down_plus.bed.score.hg19.txt..list.out.num")
hg19.up_minus <- read_dist_table("./Evolution/hg19.exon.up_minus.bed.score.hg19.txt..list.out.num")
hg19.down_minus <- read_dist_table("./Evolution/hg19.exon.down_minus.bed.score.hg19.txt..list.out.num")
hg19.up_minus[,Position:=Position*-1]
hg19.down_minus[,Position:=Position*-1]
hg19.TOTAL <- plot_density(hg19.up_plus, hg19.up_minus, hg19.down_plus, hg19.down_minus)

dm6.up_plus <- read_dist_table("./Evolution/dm6.exon.up_plus.bed.score.dm6.txt..list.out.num")
dm6.down_plus <- read_dist_table("./Evolution/dm6.exon.down_plus.bed.score.dm6.txt..list.out.num")
dm6.up_minus <- read_dist_table("./Evolution/dm6.exon.up_minus.bed.score.dm6.txt..list.out.num")
dm6.down_minus <- read_dist_table("./Evolution/dm6.exon.down_minus.bed.score.dm6.txt..list.out.num")
dm6.up_minus[,Position:=Position*-1]
dm6.down_minus[,Position:=Position*-1]
dm6.TOTAL <- plot_density(dm6.up_plus, dm6.up_minus, dm6.down_plus, dm6.down_minus)

galGal5.up_plus <- read_dist_table("./Evolution/galGal5.exon.up_plus.bed.score.galGal5.txt..list.out.num")
galGal5.down_plus <- read_dist_table("./Evolution/galGal5.exon.down_plus.bed.score.galGal5.txt..list.out.num")
galGal5.up_minus <- read_dist_table("./Evolution/galGal5.exon.up_minus.bed.score.galGal5.txt..list.out.num")
galGal5.down_minus <- read_dist_table("./Evolution/galGal5.exon.down_minus.bed.score.galGal5.txt..list.out.num")
galGal5.up_minus[,Position:=Position*-1]
galGal5.down_minus[,Position:=Position*-1]
galGal5.TOTAL <- plot_density(galGal5.up_plus, galGal5.up_minus, galGal5.down_plus, galGal5.down_minus)

sacCer.up_plus <- read_dist_table("./Evolution/sacCer3.exon.up_plus.bed.score.sacCer3.txt..list.out.num")
sacCer.down_plus <- read_dist_table("./Evolution/sacCer3.exon.down_plus.bed.score.sacCer3.txt..list.out.num")
sacCer.up_minus <- read_dist_table("./Evolution/sacCer3.exon.up_minus.bed.score.sacCer3.txt..list.out.num")
sacCer.down_minus <- read_dist_table("./Evolution/sacCer3.exon.down_minus.bed.score.sacCer3.txt..list.out.num")
sacCer.up_minus[,Position:=Position*-1]
sacCer.down_minus[,Position:=Position*-1]
sacCer.TOTAL <- plot_density(sacCer.up_plus, sacCer.up_minus, sacCer.down_plus, sacCer.down_minus)

ce10.TOTAL[, species:="C. elegans"] 
hg19.TOTAL[, species:="H. sapiens"] 
mm10.TOTAL[, species:="M. musculus"]
danRer11.TOTAL[, species:="D. rerio"] 
dm6.TOTAL[, species:="D. melanogaster"]
galGal5.TOTAL[, species:="G. gallus"]
sacCer.TOTAL[, species:="S. cerevisiae"]
xenTro9.TOTAL[ , species:="X. tropicalis" ]
anoCar2.TOTAL[  , species:="A. carolinensis" ]
TAIR10.TOTAL[  , species:="A. thaliana" ]
susScr11.TOTAL[ , species:="S. scrofa"]
All.species.TOTAL <- rbind(hg19.TOTAL, mm10.TOTAL, galGal5.TOTAL, danRer11.TOTAL, anoCar2.TOTAL, xenTro9.TOTAL,  susScr11.TOTAL  )
#All.species.TOTAL.binomial <- cbind(All.species.TOTAL,  Gruns.total[, binconf(Occurrences, hg19.nexons) ])
#All.species.TOTAL.binomial[, median:=NULL]
#All.species.TOTAL.binomial[ , median:=median(PointEst), by=c("exon_pos", "species" )]
#All.species.TOTAL.binomial[, `:=`(Enrrichment=PointEst/median, Enrrichment_l=Lower/median, Enrrichment_u=Upper/median)]
Fig6.B <- ggplot(All.species.TOTAL)+
    geom_line(aes(x=Position,y=Enrrichment, color=species)) +
    #   geom_ribbon(aes(x=Position, fill=species, ymin=Enrrichment_l, ymax=Enrrichment_u), alpha=0.3) +
    xlim(c(-300,300)) +
    facet_grid( . ~ exon_pos ) +
  theme(plot.title = element_text(hjust = 0.5)) +
  theme_bw() +
    theme(legend.position = "top", legend.direction = "horizontal") 
Fig6.B

We plot other species that did not show strong enrichment by separate

All.species.TOTAL <- rbind(hg19.TOTAL, mm10.TOTAL, galGal5.TOTAL, danRer11.TOTAL, anoCar2.TOTAL, xenTro9.TOTAL,  susScr11.TOTAL  )
Sup6.A <- ggplot(All.species.TOTAL)+
    geom_line(aes(x=Position,y=Enrrichment, color=species)) +
    #   geom_ribbon(aes(x=Position, fill=species, ymin=Enrrichment_l, ymax=Enrrichment_u), alpha=0.3) +
    xlim(c(-300,300)) +
    ggtitle( "Vertebrates") +
    facet_grid( . ~ exon_pos ) +
      labs(color="Specie") +
    theme(plot.title = element_text(hjust = 0.5)) +
    theme(legend.position = "top", legend.direction = "horizontal") 
All.species.TOTAL <- rbind(ce10.TOTAL, dm6.TOTAL, TAIR10.TOTAL  )
Sup6.B <- ggplot(All.species.TOTAL)+
    geom_line(aes(x=Position,y=Enrrichment, color=species)) +
    xlim(c(-300,300)) +
    ggtitle( "Non-vertebrates") +
      labs(color="Specie") +
    facet_grid( . ~ exon_pos ) +
  theme(plot.title = element_text(hjust = 0.5)) +
    theme(legend.position = "top", legend.direction = "horizontal") 

plot_grid(Sup6.A,Sup6.B, labels = "AUTO", ncol = 1 )

Removed 9786 row(s) containing missing values (geom_path).Removed 4194 row(s) containing missing values (geom_path).

G4 and gene structure

Flanking intron size

Here we analized the intron size of distribution of exon which are flanked by G4 (on an 100nt window)

intron_size_upstream_non_template  <- rbind(fread('./Intron_size/Introns.hg19_upstream_100nt_window.bed.plus_strand_genome.plus_G4s'),  
 fread('./Intron_size/Introns.hg19_upstream_100nt_window.bed.minus_strand_genome.minus_G4s'))
intron_size_downstream_non_template  <- rbind(fread('./Intron_size/Introns.hg19_downstream_100nt_window.bed.plus_strand_genome.plus_G4s'),  
 fread('./Intron_size/Introns.hg19_downstream_100nt_window.bed.minus_strand_genome.minus_G4s'))
intron_size_upstream_template  <- rbind(fread('./Intron_size/Introns.hg19_upstream_100nt_window.bed.plus_strand_genome.minus_G4s'),  
 fread('./Intron_size/Introns.hg19_upstream_100nt_window.bed.minus_strand_genome.plus_G4s'))
intron_size_downstream_template  <- rbind(fread('./Intron_size/Introns.hg19_downstream_100nt_window.bed.minus_strand_genome.plus_G4s'),  
 fread('./Intron_size/Introns.hg19_downstream_100nt_window.bed.plus_strand_genome.minus_G4s'))
intron_size_upstream_non_template[ , `:=`(exon_pos="upstream", strand="non_template") ]
intron_size_downstream_non_template[ , `:=`(exon_pos="downstream", strand="non_template") ]
intron_size_upstream_template[ , `:=`(exon_pos="upstream", strand="template") ]
intron_size_downstream_template[ , `:=`(exon_pos="downstream", strand="template") ]
intron_size_TOTAL <- rbind(intron_size_upstream_non_template, intron_size_downstream_non_template, intron_size_upstream_template, intron_size_downstream_template )
colnames(intron_size_TOTAL) <- c("chrom", "start", "end", "strand", "intron_number", "intron_size", "Transcript", "G4", "exon_pos", "Strand"  )

intron_size_TOTAL[  G4>0, G4_type:="With G4" ]
intron_size_TOTAL[  G4==0, G4_type:="Without G4" ]
intron_size_TOTAL$exon_pos <- factor(intron_size_TOTAL$exon_pos, levels=c("upstream", "downstream"))
Fig3.A <- ggplot(data=intron_size_TOTAL) +
  geom_boxplot( aes(x=G4_type, y=log10(intron_size) ) ) +
  facet_grid( . ~  exon_pos ) +
  xlab("")+
  ylab("log10(Intron size)") +
  theme_bw()
Fig3.A

long_introns.5ss <- fread("./Intron_size/GC_correction/long_introns.same_GC.bed.intron_5ss_.bed.closest.G4s")

Error in fread("./Intron_size/GC_correction/long_introns.same_GC.bed.intron_5ss_.bed.closest.G4s") : 
  File './Intron_size/GC_correction/long_introns.same_GC.bed.intron_5ss_.bed.closest.G4s' does not exist or is non-readable. getwd()=='/Users/gp7/Google_Drive/Results/Non_B/Georgakopoulos_Soares_and_Parada_2019'

short_long.odd_ratios <- c()
short_long.pvalues<- c()
short_long.long.fraq <- c()
short_long.short.fraq <- c()
  
short_long.GCs <- data.table()
  
for (i in seq(1, length(i.mins))) {
    
  i.min = i.mins[i]
  i.max = i.maxs[i]
    
  long_introns.int <- long_introns[i.id %in% long_short_correspondence_35K[s.len>i.min & s.len<=i.max ,  l.id]]
  short_introns.int <- short_introns[i.id %in% long_short_correspondence_35K[s.len>i.min & s.len<=i.max, s.id]]
  
  
  long_short.int.2x2 <- matrix(nrow = 2, c(nrow(long_introns.int[(!G4.3ss & !G4.5ss), ]),
                                           nrow(short_introns.int[(!G4.3ss & !G4.5ss), ]),
                                           nrow(long_introns.int[(G4.3ss | G4.5ss), ]),
                                           nrow(short_introns.int[(G4.3ss | G4.5ss), ]) ))
  
  
  odd.ratio <- (long_short.int.2x2[2,2] / long_short.int.2x2[2,1] ) / (long_short.int.2x2[1,2] / long_short.int.2x2[1,1])
  long.frac <-  (long_short.int.2x2[1,2] / long_short.int.2x2[1,1])
  short.frac <- (long_short.int.2x2[2,2] / long_short.int.2x2[2,1] )
  
  print(odd.ratio)
  print(chisq.test(long_short.int.2x2))
  
  short_long.odd_ratios <- c(short_long.odd_ratios, odd.ratio)
  short_long.pvalues <- c(short_long.pvalues, chisq.test(long_short.int.2x2)$p.value * length(i.mins))
  short_long.short.fraq  <- c(short_long.short.fraq, short.frac)
  short_long.long.fraq  <- c(short_long.long.fraq, long.frac)
  
  
  short_long.GCs <- rbind( short_long.GCs, short_introns.int[ , .(i.id, i.GC, G4, type="Short",  i.min=i.min, i.max=i.max )] )
  short_long.GCs <- rbind( short_long.GCs, long_introns.int[ , .(i.id, i.GC, G4, type="Long",  i.min=i.min, i.max=i.max )] )  
  }

[1] 0.8138132

    Pearson's Chi-squared test with Yates' continuity correction

data:  long_short.int.2x2
X-squared = 9.4403, df = 1, p-value = 0.002123

[1] 1.064866

    Pearson's Chi-squared test with Yates' continuity correction

data:  long_short.int.2x2
X-squared = 0.81801, df = 1, p-value = 0.3658

[1] 0.7789226

    Pearson's Chi-squared test with Yates' continuity correction

data:  long_short.int.2x2
X-squared = 8.7143, df = 1, p-value = 0.003157

[1] 0.9686031

    Pearson's Chi-squared test with Yates' continuity correction

data:  long_short.int.2x2
X-squared = 0.10585, df = 1, p-value = 0.7449

[1] 0.7346991

    Pearson's Chi-squared test with Yates' continuity correction

data:  long_short.int.2x2
X-squared = 10.563, df = 1, p-value = 0.001154

[1] 0.8126509

    Pearson's Chi-squared test with Yates' continuity correction

data:  long_short.int.2x2
X-squared = 4.5242, df = 1, p-value = 0.03342

[1] 0.8175824

    Pearson's Chi-squared test with Yates' continuity correction

data:  long_short.int.2x2
X-squared = 3.3907, df = 1, p-value = 0.06556

[1] 0.8382815

    Pearson's Chi-squared test with Yates' continuity correction

data:  long_short.int.2x2
X-squared = 2.2925, df = 1, p-value = 0.13

[1] 0.8045027

    Pearson's Chi-squared test with Yates' continuity correction

data:  long_short.int.2x2
X-squared = 3.0408, df = 1, p-value = 0.08119

short_long.res <- data.table(short_long.odd_ratios, short_long.pvalues, i.mins, i.maxs, short_long.short.fraq, short_long.long.fraq)
short_long.res.melt <- melt(short_long.res, id=c("short_long.odd_ratios","short_long.pvalues", "i.mins", "i.maxs"))

short_long.res.melt[, sig:=""]
short_long.res.melt[short_long.pvalues <= 0.05 , sig:="*"]
short_long.res.melt[short_long.pvalues <= 0.005 , sig:="**"]
short_long.res.melt[short_long.pvalues <= 0.000 , sig:="***"]
sig_rows <- short_long.res.melt[variable=="short_long.short.fraq" & sig!="", which = TRUE]
sig_anno <- short_long.res.melt[variable=="short_long.short.fraq" & sig!="", sig]
Fig3.C.new <-  ggplot(short_long.res.melt, aes(as.factor(i.mins), value)) +
  geom_bar(aes( group=variable, fill=variable), position="dodge", stat="identity") +
  geom_signif( y_position=0.3, xmin=sig_rows-0.15, xmax=sig_rows+0.15, annotation=sig_anno, tip_length=0) +
  scale_fill_discrete(name = "Intron type", labels = c("Short", "Long")) +
  scale_fill_brewer(palette = 'Blues') +
  theme(legend.position = "top", legend.direction = "horizontal") 

Scale for 'fill' is already present. Adding another scale for 'fill', which will replace the existing scale.

Fig3.C.new

Exon number

Here we explored how G4 enrichments change thorugh gene body

Exon numbers by stratnds

exons_1.up_plus.nt <- read_dist_table("./exon_numbers/strands/exons_1_plus_strand_upstream.txt.score.G4_plus.bed.list.out.num")
exons_1.down_plus.nt <- read_dist_table("./exon_numbers/strands/exons_1_plus_strand_downstream.txt.score.G4_plus.bed.list.out.num")
exons_1.up_minus.nt <- read_dist_table("./exon_numbers/strands/exons_1_minus_strand_upstream.txt.score.G4_minus.bed.list.out.num")
exons_1.down_minus.nt <- read_dist_table("./exon_numbers/strands/exons_1_minus_strand_downstream.txt.score.G4_minus.bed.list.out.num")
exons_1.up_minus.nt[,Position:=Position*-1]
exons_1.down_minus.nt[,Position:=Position*-1]
exons_1.TOTAL.nt <- plot_density(exons_1.up_plus.nt, exons_1.up_minus.nt, exons_1.down_plus.nt, exons_1.down_minus.nt) 

exons_1.up_plus.t <- read_dist_table("./exon_numbers/strands/exons_1_plus_strand_upstream.txt.score.G4_minus.bed.list.out.num")
exons_1.down_plus.t <- read_dist_table("./exon_numbers/strands/exons_1_plus_strand_downstream.txt.score.G4_minus.bed.list.out.num")
exons_1.up_minus.t <- read_dist_table("./exon_numbers/strands/exons_1_minus_strand_upstream.txt.score.G4_plus.bed.list.out.num")
exons_1.down_minus.t <- read_dist_table("./exon_numbers/strands/exons_1_minus_strand_downstream.txt.score.G4_plus.bed.list.out.num")
exons_1.up_minus.t[,Position:=Position*-1]
exons_1.down_minus.t[,Position:=Position*-1]
exons_1.TOTAL.t <- plot_density(exons_1.up_plus.t, exons_1.up_minus.t, exons_1.down_plus.t, exons_1.down_minus.t) 

 ggplot(exons_1.TOTAL.t)+
    geom_line(aes(x=Position,y=Enrrichment)) +
    facet_grid( . ~ exon_pos ) +
    ylim(c(0,6)) +
    theme_bw()

exons_2.up_plus.nt <- read_dist_table("./exon_numbers/strands/exons_2_plus_strand_upstream.txt.score.G4_plus.bed.list.out.num")
exons_2.down_plus.nt <- read_dist_table("./exon_numbers/strands/exons_2_plus_strand_downstream.txt.score.G4_plus.bed.list.out.num")
exons_2.up_minus.nt <- read_dist_table("./exon_numbers/strands/exons_2_minus_strand_upstream.txt.score.G4_minus.bed.list.out.num")
exons_2.down_minus.nt <- read_dist_table("./exon_numbers/strands/exons_2_minus_strand_downstream.txt.score.G4_minus.bed.list.out.num")
exons_2.up_minus.nt[,Position:=Position*-1]
exons_2.down_minus.nt[,Position:=Position*-1]
exons_2.TOTAL.nt <- plot_density(exons_2.up_plus.nt, exons_2.up_minus.nt, exons_2.down_plus.nt, exons_2.down_minus.nt) 

exons_2.up_plus.t <- read_dist_table("./exon_numbers/strands/exons_2_plus_strand_upstream.txt.score.G4_minus.bed.list.out.num")
exons_2.down_plus.t <- read_dist_table("./exon_numbers/strands/exons_2_plus_strand_downstream.txt.score.G4_minus.bed.list.out.num")
exons_2.up_minus.t <- read_dist_table("./exon_numbers/strands/exons_2_minus_strand_upstream.txt.score.G4_plus.bed.list.out.num")
exons_2.down_minus.t <- read_dist_table("./exon_numbers/strands/exons_2_minus_strand_downstream.txt.score.G4_plus.bed.list.out.num")
exons_2.up_minus.t[,Position:=Position*-1]
exons_2.down_minus.t[,Position:=Position*-1]
exons_2.TOTAL.t <- plot_density(exons_2.up_plus.t, exons_2.up_minus.t, exons_2.down_plus.t, exons_2.down_minus.t) 

 ggplot(exons_2.TOTAL.t)+
    geom_line(aes(x=Position,y=Enrrichment)) +
    facet_grid( . ~ exon_pos ) +
    ylim(c(0,6)) +
    theme_bw()

exons_3.up_plus.nt <- read_dist_table("./exon_numbers/strands/exons_3_plus_strand_upstream.txt.score.G4_plus.bed.list.out.num")
exons_3.down_plus.nt <- read_dist_table("./exon_numbers/strands/exons_3_plus_strand_downstream.txt.score.G4_plus.bed.list.out.num")
exons_3.up_minus.nt <- read_dist_table("./exon_numbers/strands/exons_3_minus_strand_upstream.txt.score.G4_minus.bed.list.out.num")
exons_3.down_minus.nt <- read_dist_table("./exon_numbers/strands/exons_3_minus_strand_downstream.txt.score.G4_minus.bed.list.out.num")
exons_3.up_minus.nt[,Position:=Position*-1]
exons_3.down_minus.nt[,Position:=Position*-1]
exons_3.TOTAL.nt <- plot_density(exons_3.up_plus.nt, exons_3.up_minus.nt, exons_3.down_plus.nt, exons_3.down_minus.nt) 

exons_3.up_plus.t <- read_dist_table("./exon_numbers/strands/exons_3_plus_strand_upstream.txt.score.G4_minus.bed.list.out.num")
exons_3.down_plus.t <- read_dist_table("./exon_numbers/strands/exons_3_plus_strand_downstream.txt.score.G4_minus.bed.list.out.num")
exons_3.up_minus.t <- read_dist_table("./exon_numbers/strands/exons_3_minus_strand_upstream.txt.score.G4_plus.bed.list.out.num")
exons_3.down_minus.t <- read_dist_table("./exon_numbers/strands/exons_3_minus_strand_downstream.txt.score.G4_plus.bed.list.out.num")
exons_3.up_minus.t[,Position:=Position*-1]
exons_3.down_minus.t[,Position:=Position*-1]
exons_3.TOTAL.t <- plot_density(exons_3.up_plus.t, exons_3.up_minus.t, exons_3.down_plus.t, exons_3.down_minus.t) 

 ggplot(exons_3.TOTAL.t)+
    geom_line(aes(x=Position,y=Enrrichment)) +
    facet_grid( . ~ exon_pos ) +
    ylim(c(0,6)) +
    theme_bw()

exons_4.up_plus.nt <- read_dist_table("./exon_numbers/strands/exons_4_plus_strand_upstream.txt.score.G4_plus.bed.list.out.num")
exons_4.down_plus.nt <- read_dist_table("./exon_numbers/strands/exons_4_plus_strand_downstream.txt.score.G4_plus.bed.list.out.num")
exons_4.up_minus.nt <- read_dist_table("./exon_numbers/strands/exons_4_minus_strand_upstream.txt.score.G4_minus.bed.list.out.num")
exons_4.down_minus.nt <- read_dist_table("./exon_numbers/strands/exons_4_minus_strand_downstream.txt.score.G4_minus.bed.list.out.num")
exons_4.up_minus.nt[,Position:=Position*-1]
exons_4.down_minus.nt[,Position:=Position*-1]
exons_4.TOTAL.nt <- plot_density(exons_4.up_plus.nt, exons_4.up_minus.nt, exons_4.down_plus.nt, exons_4.down_minus.nt) 

exons_4.up_plus.t <- read_dist_table("./exon_numbers/strands/exons_4_plus_strand_upstream.txt.score.G4_minus.bed.list.out.num")
exons_4.down_plus.t <- read_dist_table("./exon_numbers/strands/exons_4_plus_strand_downstream.txt.score.G4_minus.bed.list.out.num")
exons_4.up_minus.t <- read_dist_table("./exon_numbers/strands/exons_4_minus_strand_upstream.txt.score.G4_plus.bed.list.out.num")
exons_4.down_minus.t <- read_dist_table("./exon_numbers/strands/exons_4_minus_strand_downstream.txt.score.G4_plus.bed.list.out.num")
exons_4.up_minus.t[,Position:=Position*-1]
exons_4.down_minus.t[,Position:=Position*-1]
exons_4.TOTAL.t <- plot_density(exons_4.up_plus.t, exons_4.up_minus.t, exons_4.down_plus.t, exons_4.down_minus.t) 

 ggplot(exons_4.TOTAL.t)+
    geom_line(aes(x=Position,y=Enrrichment)) +
    facet_grid( . ~ exon_pos ) +
    ylim(c(0,6)) +
    theme_bw()

exons_middle.up_plus.nt <- read_dist_table("./exon_numbers/strands/exons_middle_plus_strand_upstream.txt.score.G4_plus.bed.list.out.num")
exons_middle.down_plus.nt <- read_dist_table("./exon_numbers/strands/exons_middle_plus_strand_downstream.txt.score.G4_plus.bed.list.out.num")
exons_middle.up_minus.nt <- read_dist_table("./exon_numbers/strands/exons_middle_minus_strand_upstream.txt.score.G4_minus.bed.list.out.num")
exons_middle.down_minus.nt <- read_dist_table("./exon_numbers/strands/exons_middle_minus_strand_downstream.txt.score.G4_minus.bed.list.out.num")
exons_middle.up_minus.nt[,Position:=Position*-1]
exons_middle.down_minus.nt[,Position:=Position*-1]
exons_middle.TOTAL.nt <- plot_density(exons_middle.up_plus.nt, exons_middle.up_minus.nt, exons_middle.down_plus.nt, exons_middle.down_minus.nt) 

exons_middle.up_plus.t <- read_dist_table("./exon_numbers/strands/exons_middle_plus_strand_upstream.txt.score.G4_minus.bed.list.out.num")
exons_middle.down_plus.t <- read_dist_table("./exon_numbers/strands/exons_middle_plus_strand_downstream.txt.score.G4_minus.bed.list.out.num")
exons_middle.up_minus.t <- read_dist_table("./exon_numbers/strands/exons_middle_minus_strand_upstream.txt.score.G4_plus.bed.list.out.num")
exons_middle.down_minus.t <- read_dist_table("./exon_numbers/strands/exons_middle_minus_strand_downstream.txt.score.G4_plus.bed.list.out.num")
exons_middle.up_minus.t[,Position:=Position*-1]
exons_middle.down_minus.t[,Position:=Position*-1]
exons_middle.TOTAL.t <- plot_density(exons_middle.up_plus.t, exons_middle.up_minus.t, exons_middle.down_plus.t, exons_middle.down_minus.t) 

 ggplot(exons_middle.TOTAL.t)+
    geom_line(aes(x=Position,y=Enrrichment)) +
    facet_grid( . ~ exon_pos ) +
    ylim(c(0,6)) +
    theme_bw()

exons_minus4.up_plus.nt <- read_dist_table("./exon_numbers/strands/exons_minus4_plus_strand_upstream.txt.score.G4_plus.bed.list.out.num")
exons_minus4.down_plus.nt <- read_dist_table("./exon_numbers/strands/exons_minus4_plus_strand_downstream.txt.score.G4_plus.bed.list.out.num")
exons_minus4.up_minus.nt <- read_dist_table("./exon_numbers/strands/exons_minus4_minus_strand_upstream.txt.score.G4_minus.bed.list.out.num")
exons_minus4.down_minus.nt <- read_dist_table("./exon_numbers/strands/exons_minus4_minus_strand_downstream.txt.score.G4_minus.bed.list.out.num")
exons_minus4.up_minus.nt[,Position:=Position*-1]
exons_minus4.down_minus.nt[,Position:=Position*-1]
exons_minus4.TOTAL.nt <- plot_density(exons_minus4.up_plus.nt, exons_minus4.up_minus.nt, exons_minus4.down_plus.nt, exons_minus4.down_minus.nt) 

exons_minus4.up_plus.t <- read_dist_table("./exon_numbers/strands/exons_minus4_plus_strand_upstream.txt.score.G4_minus.bed.list.out.num")
exons_minus4.down_plus.t <- read_dist_table("./exon_numbers/strands/exons_minus4_plus_strand_downstream.txt.score.G4_minus.bed.list.out.num")
exons_minus4.up_minus.t <- read_dist_table("./exon_numbers/strands/exons_minus4_minus_strand_upstream.txt.score.G4_plus.bed.list.out.num")
exons_minus4.down_minus.t <- read_dist_table("./exon_numbers/strands/exons_minus4_minus_strand_downstream.txt.score.G4_plus.bed.list.out.num")
exons_minus4.up_minus.t[,Position:=Position*-1]
exons_minus4.down_minus.t[,Position:=Position*-1]
exons_minus4.TOTAL.t <- plot_density(exons_minus4.up_plus.t, exons_minus4.up_minus.t, exons_minus4.down_plus.t, exons_minus4.down_minus.t) 

 ggplot(exons_minus4.TOTAL.t)+
    geom_line(aes(x=Position,y=Enrrichment)) +
    facet_grid( . ~ exon_pos ) +
    ylim(c(0,6)) +
    theme_bw()

exons_minus3.up_plus.nt <- read_dist_table("./exon_numbers/strands/exons_minus3_plus_strand_upstream.txt.score.G4_plus.bed.list.out.num")
exons_minus3.down_plus.nt <- read_dist_table("./exon_numbers/strands/exons_minus3_plus_strand_downstream.txt.score.G4_plus.bed.list.out.num")
exons_minus3.up_minus.nt <- read_dist_table("./exon_numbers/strands/exons_minus3_minus_strand_upstream.txt.score.G4_minus.bed.list.out.num")
exons_minus3.down_minus.nt <- read_dist_table("./exon_numbers/strands/exons_minus3_minus_strand_downstream.txt.score.G4_minus.bed.list.out.num")
exons_minus3.up_minus.nt[,Position:=Position*-1]
exons_minus3.down_minus.nt[,Position:=Position*-1]
exons_minus3.TOTAL.nt <- plot_density(exons_minus3.up_plus.nt, exons_minus3.up_minus.nt, exons_minus3.down_plus.nt, exons_minus3.down_minus.nt) 

exons_minus3.up_plus.t <- read_dist_table("./exon_numbers/strands/exons_minus3_plus_strand_upstream.txt.score.G4_minus.bed.list.out.num")
exons_minus3.down_plus.t <- read_dist_table("./exon_numbers/strands/exons_minus3_plus_strand_downstream.txt.score.G4_minus.bed.list.out.num")
exons_minus3.up_minus.t <- read_dist_table("./exon_numbers/strands/exons_minus3_minus_strand_upstream.txt.score.G4_plus.bed.list.out.num")
exons_minus3.down_minus.t <- read_dist_table("./exon_numbers/strands/exons_minus3_minus_strand_downstream.txt.score.G4_plus.bed.list.out.num")
exons_minus3.up_minus.t[,Position:=Position*-1]
exons_minus3.down_minus.t[,Position:=Position*-1]
exons_minus3.TOTAL.t <- plot_density(exons_minus3.up_plus.t, exons_minus3.up_minus.t, exons_minus3.down_plus.t, exons_minus3.down_minus.t) 

 ggplot(exons_minus3.TOTAL.t)+
    geom_line(aes(x=Position,y=Enrrichment)) +
    facet_grid( . ~ exon_pos ) +
    ylim(c(0,6)) +
    theme_bw()

exons_minus2.up_plus.nt <- read_dist_table("./exon_numbers/strands/exons_minus2_plus_strand_upstream.txt.score.G4_plus.bed.list.out.num")
exons_minus2.down_plus.nt <- read_dist_table("./exon_numbers/strands/exons_minus2_plus_strand_downstream.txt.score.G4_plus.bed.list.out.num")
exons_minus2.up_minus.nt <- read_dist_table("./exon_numbers/strands/exons_minus2_minus_strand_upstream.txt.score.G4_minus.bed.list.out.num")
exons_minus2.down_minus.nt <- read_dist_table("./exon_numbers/strands/exons_minus2_minus_strand_downstream.txt.score.G4_minus.bed.list.out.num")
exons_minus2.up_minus.nt[,Position:=Position*-1]
exons_minus2.down_minus.nt[,Position:=Position*-1]
exons_minus2.TOTAL.nt <- plot_density(exons_minus2.up_plus.nt, exons_minus2.up_minus.nt, exons_minus2.down_plus.nt, exons_minus2.down_minus.nt) 

exons_minus2.up_plus.t <- read_dist_table("./exon_numbers/strands/exons_minus2_plus_strand_upstream.txt.score.G4_minus.bed.list.out.num")
exons_minus2.down_plus.t <- read_dist_table("./exon_numbers/strands/exons_minus2_plus_strand_downstream.txt.score.G4_minus.bed.list.out.num")
exons_minus2.up_minus.t <- read_dist_table("./exon_numbers/strands/exons_minus2_minus_strand_upstream.txt.score.G4_plus.bed.list.out.num")
exons_minus2.down_minus.t <- read_dist_table("./exon_numbers/strands/exons_minus2_minus_strand_downstream.txt.score.G4_plus.bed.list.out.num")
exons_minus2.up_minus.t[,Position:=Position*-1]
exons_minus2.down_minus.t[,Position:=Position*-1]
exons_minus2.TOTAL.t <- plot_density(exons_minus2.up_plus.t, exons_minus2.up_minus.t, exons_minus2.down_plus.t, exons_minus2.down_minus.t) 

 ggplot(exons_minus2.TOTAL.t)+
    geom_line(aes(x=Position,y=Enrrichment)) +
    facet_grid( . ~ exon_pos ) +
    ylim(c(0,6)) +
    theme_bw()

exons_minus1.up_plus.nt <- read_dist_table("./exon_numbers/strands/exons_minus1_plus_strand_upstream.txt.score.G4_plus.bed.list.out.num")
exons_minus1.down_plus.nt <- read_dist_table("./exon_numbers/strands/exons_minus1_plus_strand_downstream.txt.score.G4_plus.bed.list.out.num")
exons_minus1.up_minus.nt <- read_dist_table("./exon_numbers/strands/exons_minus1_minus_strand_upstream.txt.score.G4_minus.bed.list.out.num")
exons_minus1.down_minus.nt <- read_dist_table("./exon_numbers/strands/exons_minus1_minus_strand_downstream.txt.score.G4_minus.bed.list.out.num")
exons_minus1.up_minus.nt[,Position:=Position*-1]
exons_minus1.down_minus.nt[,Position:=Position*-1]
exons_minus1.TOTAL.nt <- plot_density(exons_minus1.up_plus.nt, exons_minus1.up_minus.nt, exons_minus1.down_plus.nt, exons_minus1.down_minus.nt) 

exons_minus1.up_plus.t <- read_dist_table("./exon_numbers/strands/exons_minus1_plus_strand_upstream.txt.score.G4_minus.bed.list.out.num")
exons_minus1.down_plus.t <- read_dist_table("./exon_numbers/strands/exons_minus1_plus_strand_downstream.txt.score.G4_minus.bed.list.out.num")
exons_minus1.up_minus.t <- read_dist_table("./exon_numbers/strands/exons_minus1_minus_strand_upstream.txt.score.G4_plus.bed.list.out.num")
exons_minus1.down_minus.t <- read_dist_table("./exon_numbers/strands/exons_minus1_minus_strand_downstream.txt.score.G4_plus.bed.list.out.num")
exons_minus1.up_minus.t[,Position:=Position*-1]
exons_minus1.down_minus.t[,Position:=Position*-1]
exons_minus1.TOTAL.t <- plot_density(exons_minus1.up_plus.t, exons_minus1.up_minus.t, exons_minus1.down_plus.t, exons_minus1.down_minus.t) 

 ggplot(exons_minus1.TOTAL.t)+
    geom_line(aes(x=Position,y=Enrrichment)) +
    facet_grid( . ~ exon_pos ) +
    ylim(c(0,6)) +
    theme_bw()

G4 seq

Here we distribution of G4-seq experiments

G4_2019.PDS.Q1_up_plus <- read_dist_table("./G4_seq_2019/exon.up_plus.q1.bed.score.GSM3003540_Homo_all_w15_th-1_plus_minus.hits.max.PDS.w50.35.bed.bed.list.out.num")
G4_2019.PDS.Q2_up_plus <- read_dist_table("./G4_seq_2019/exon.up_plus.q2.bed.score.GSM3003540_Homo_all_w15_th-1_plus_minus.hits.max.PDS.w50.35.bed.bed.list.out.num")
G4_2019.PDS.Q3_up_plus <- read_dist_table("./G4_seq_2019/exon.up_plus.q3.bed.score.GSM3003540_Homo_all_w15_th-1_plus_minus.hits.max.PDS.w50.35.bed.bed.list.out.num")
G4_2019.PDS.Q4_up_plus <- read_dist_table("./G4_seq_2019/exon.up_plus.q4.bed.score.GSM3003540_Homo_all_w15_th-1_plus_minus.hits.max.PDS.w50.35.bed.bed.list.out.num")
G4_2019.PDS.Q1_down_plus <- read_dist_table("./G4_seq_2019/exon.down_plus.q1.bed.score.GSM3003540_Homo_all_w15_th-1_plus_minus.hits.max.PDS.w50.35.bed.bed.list.out.num")
G4_2019.PDS.Q2_down_plus <- read_dist_table("./G4_seq_2019/exon.down_plus.q2.bed.score.GSM3003540_Homo_all_w15_th-1_plus_minus.hits.max.PDS.w50.35.bed.bed.list.out.num")
G4_2019.PDS.Q3_down_plus <- read_dist_table("./G4_seq_2019/exon.down_plus.q3.bed.score.GSM3003540_Homo_all_w15_th-1_plus_minus.hits.max.PDS.w50.35.bed.bed.list.out.num")
G4_2019.PDS.Q4_down_plus <- read_dist_table("./G4_seq_2019/exon.down_plus.q4.bed.score.GSM3003540_Homo_all_w15_th-1_plus_minus.hits.max.PDS.w50.35.bed.bed.list.out.num")
G4_2019.PDS.Q1_up_minus <- read_dist_table("./G4_seq_2019/exon.up_minus.q1.bed.score.GSM3003540_Homo_all_w15_th-1_plus_minus.hits.max.PDS.w50.35.bed.bed.list.out.num")
G4_2019.PDS.Q2_up_minus <- read_dist_table("./G4_seq_2019/exon.up_minus.q2.bed.score.GSM3003540_Homo_all_w15_th-1_plus_minus.hits.max.PDS.w50.35.bed.bed.list.out.num")
G4_2019.PDS.Q3_up_minus <- read_dist_table("./G4_seq_2019/exon.up_minus.q3.bed.score.GSM3003540_Homo_all_w15_th-1_plus_minus.hits.max.PDS.w50.35.bed.bed.list.out.num")
G4_2019.PDS.Q4_up_minus <- read_dist_table("./G4_seq_2019/exon.up_minus.q4.bed.score.GSM3003540_Homo_all_w15_th-1_plus_minus.hits.max.PDS.w50.35.bed.bed.list.out.num")
G4_2019.PDS.Q1_down_minus <- read_dist_table("./G4_seq_2019/exon.down_minus.q1.bed.score.GSM3003540_Homo_all_w15_th-1_plus_minus.hits.max.PDS.w50.35.bed.bed.list.out.num")
G4_2019.PDS.Q2_down_minus <- read_dist_table("./G4_seq_2019/exon.down_minus.q2.bed.score.GSM3003540_Homo_all_w15_th-1_plus_minus.hits.max.PDS.w50.35.bed.bed.list.out.num")
G4_2019.PDS.Q3_down_minus <- read_dist_table("./G4_seq_2019/exon.down_minus.q3.bed.score.GSM3003540_Homo_all_w15_th-1_plus_minus.hits.max.PDS.w50.35.bed.bed.list.out.num")
G4_2019.PDS.Q4_down_minus <- read_dist_table("./G4_seq_2019/exon.down_minus.q4.bed.score.GSM3003540_Homo_all_w15_th-1_plus_minus.hits.max.PDS.w50.35.bed.bed.list.out.num")
G4_2019.PDS.Qs.plus.up.list <- list(G4_2019.PDS.Q1_up_plus, G4_2019.PDS.Q2_up_plus, G4_2019.PDS.Q3_up_plus, G4_2019.PDS.Q4_up_plus)
G4_2019.PDS.Qs.minus.list <- list(G4_2019.PDS.Q1_up_minus, G4_2019.PDS.Q2_up_minus, G4_2019.PDS.Q3_up_minus, G4_2019.PDS.Q4_up_minus)
G4_2019.PDS.Qs.plus.down.list <- list(G4_2019.PDS.Q1_down_plus, G4_2019.PDS.Q2_down_plus, G4_2019.PDS.Q3_down_plus, G4_2019.PDS.Q4_down_plus)
G4_2019.PDS.Qs.minus.down.list <- list(G4_2019.PDS.Q1_down_minus, G4_2019.PDS.Q2_down_minus, G4_2019.PDS.Q3_down_minus, G4_2019.PDS.Q4_down_minus)
G4_2019.PDS.window_len = 2000
G4_2019.PDS.Qs.total <- get_total_Qs(G4_2019.PDS.Qs.plus.up.list, G4_2019.PDS.Qs.minus.list, G4_2019.PDS.Qs.plus.down.list, G4_2019.PDS.Qs.minus.down.list, G4_2019.PDS.window_len)
ggplot(G4_2019.PDS.Qs.total)+
  geom_line(aes(x=Position,y=Enrrichment, colour=Q)) +
  xlim(c(-200,200)) +
  facet_grid( . ~ exon_pos ) +
  theme(text = element_text(size=15)) +
  theme_bw() + 
  labs(colour = "Splice site stregth quartile") +
  theme(legend.position = "top", legend.direction = "horizontal")

G4_2019.template.PDS.Q1_up_plus <- read_dist_table("./G4_seq_2019/exon.up_plus.q1.bed.score.GSM3003540_Homo_all_w15_th-1_minus.hits.max.PDS.w50.35.bed.bed.list.out.num")
G4_2019.template.PDS.Q2_up_plus <- read_dist_table("./G4_seq_2019/exon.up_plus.q2.bed.score.GSM3003540_Homo_all_w15_th-1_minus.hits.max.PDS.w50.35.bed.bed.list.out.num")
G4_2019.template.PDS.Q3_up_plus <- read_dist_table("./G4_seq_2019/exon.up_plus.q3.bed.score.GSM3003540_Homo_all_w15_th-1_minus.hits.max.PDS.w50.35.bed.bed.list.out.num")
G4_2019.template.PDS.Q4_up_plus <- read_dist_table("./G4_seq_2019/exon.up_plus.q4.bed.score.GSM3003540_Homo_all_w15_th-1_minus.hits.max.PDS.w50.35.bed.bed.list.out.num")
G4_2019.template.PDS.Q1_up_minus <- read_dist_table("./G4_seq_2019/exon.up_minus.q1.bed.score.GSM3003540_Homo_all_w15_th-1_plus.hits.max.PDS.w50.35.bed.bed.list.out.num")
G4_2019.template.PDS.Q2_up_minus <- read_dist_table("./G4_seq_2019/exon.up_minus.q2.bed.score.GSM3003540_Homo_all_w15_th-1_plus.hits.max.PDS.w50.35.bed.bed.list.out.num")
G4_2019.template.PDS.Q3_up_minus <- read_dist_table("./G4_seq_2019/exon.up_minus.q3.bed.score.GSM3003540_Homo_all_w15_th-1_plus.hits.max.PDS.w50.35.bed.bed.list.out.num")
G4_2019.template.PDS.Q4_up_minus <- read_dist_table("./G4_seq_2019/exon.up_minus.q4.bed.score.GSM3003540_Homo_all_w15_th-1_plus.hits.max.PDS.w50.35.bed.bed.list.out.num")
G4_2019.non_template.PDS.Q1_up_plus <- read_dist_table("./G4_seq_2019/exon.up_plus.q1.bed.score.GSM3003540_Homo_all_w15_th-1_plus.hits.max.PDS.w50.35.bed.bed.list.out.num")
G4_2019.non_template.PDS.Q2_up_plus <- read_dist_table("./G4_seq_2019/exon.up_plus.q2.bed.score.GSM3003540_Homo_all_w15_th-1_plus.hits.max.PDS.w50.35.bed.bed.list.out.num")
G4_2019.non_template.PDS.Q3_up_plus <- read_dist_table("./G4_seq_2019/exon.up_plus.q3.bed.score.GSM3003540_Homo_all_w15_th-1_plus.hits.max.PDS.w50.35.bed.bed.list.out.num")
G4_2019.non_template.PDS.Q4_up_plus <- read_dist_table("./G4_seq_2019/exon.up_plus.q4.bed.score.GSM3003540_Homo_all_w15_th-1_plus.hits.max.PDS.w50.35.bed.bed.list.out.num")
G4_2019.non_template.PDS.Q1_up_minus <- read_dist_table("./G4_seq_2019/exon.up_minus.q1.bed.score.GSM3003540_Homo_all_w15_th-1_minus.hits.max.PDS.w50.35.bed.bed.list.out.num")
G4_2019.non_template.PDS.Q2_up_minus <- read_dist_table("./G4_seq_2019/exon.up_minus.q2.bed.score.GSM3003540_Homo_all_w15_th-1_minus.hits.max.PDS.w50.35.bed.bed.list.out.num")
G4_2019.non_template.PDS.Q3_up_minus <- read_dist_table("./G4_seq_2019/exon.up_minus.q3.bed.score.GSM3003540_Homo_all_w15_th-1_minus.hits.max.PDS.w50.35.bed.bed.list.out.num")
G4_2019.non_template.PDS.Q4_up_minus <- read_dist_table("./G4_seq_2019/exon.up_minus.q4.bed.score.GSM3003540_Homo_all_w15_th-1_minus.hits.max.PDS.w50.35.bed.bed.list.out.num")
G4_2019.template.PDS.Q1_down_plus <- read_dist_table("./G4_seq_2019/exon.down_plus.q1.bed.score.GSM3003540_Homo_all_w15_th-1_minus.hits.max.PDS.w50.35.bed.bed.list.out.num")
G4_2019.template.PDS.Q2_down_plus <- read_dist_table("./G4_seq_2019/exon.down_plus.q2.bed.score.GSM3003540_Homo_all_w15_th-1_minus.hits.max.PDS.w50.35.bed.bed.list.out.num")
G4_2019.template.PDS.Q3_down_plus <- read_dist_table("./G4_seq_2019/exon.down_plus.q3.bed.score.GSM3003540_Homo_all_w15_th-1_minus.hits.max.PDS.w50.35.bed.bed.list.out.num")
G4_2019.template.PDS.Q4_down_plus <- read_dist_table("./G4_seq_2019/exon.down_plus.q4.bed.score.GSM3003540_Homo_all_w15_th-1_minus.hits.max.PDS.w50.35.bed.bed.list.out.num")
G4_2019.template.PDS.Q1_down_minus <- read_dist_table("./G4_seq_2019/exon.down_minus.q1.bed.score.GSM3003540_Homo_all_w15_th-1_plus.hits.max.PDS.w50.35.bed.bed.list.out.num")
G4_2019.template.PDS.Q2_down_minus <- read_dist_table("./G4_seq_2019/exon.down_minus.q2.bed.score.GSM3003540_Homo_all_w15_th-1_plus.hits.max.PDS.w50.35.bed.bed.list.out.num")
G4_2019.template.PDS.Q3_down_minus <- read_dist_table("./G4_seq_2019/exon.down_minus.q3.bed.score.GSM3003540_Homo_all_w15_th-1_plus.hits.max.PDS.w50.35.bed.bed.list.out.num")
G4_2019.template.PDS.Q4_down_minus <- read_dist_table("./G4_seq_2019/exon.down_minus.q4.bed.score.GSM3003540_Homo_all_w15_th-1_plus.hits.max.PDS.w50.35.bed.bed.list.out.num")
G4_2019.non_template.PDS.Q1_down_plus <- read_dist_table("./G4_seq_2019/exon.down_plus.q1.bed.score.GSM3003540_Homo_all_w15_th-1_plus.hits.max.PDS.w50.35.bed.bed.list.out.num")
G4_2019.non_template.PDS.Q2_down_plus <- read_dist_table("./G4_seq_2019/exon.down_plus.q2.bed.score.GSM3003540_Homo_all_w15_th-1_plus.hits.max.PDS.w50.35.bed.bed.list.out.num")
G4_2019.non_template.PDS.Q3_down_plus <- read_dist_table("./G4_seq_2019/exon.down_plus.q3.bed.score.GSM3003540_Homo_all_w15_th-1_plus.hits.max.PDS.w50.35.bed.bed.list.out.num")
G4_2019.non_template.PDS.Q4_down_plus <- read_dist_table("./G4_seq_2019/exon.down_plus.q4.bed.score.GSM3003540_Homo_all_w15_th-1_plus.hits.max.PDS.w50.35.bed.bed.list.out.num")
G4_2019.non_template.PDS.Q1_down_minus <- read_dist_table("./G4_seq_2019/exon.down_minus.q1.bed.score.GSM3003540_Homo_all_w15_th-1_minus.hits.max.PDS.w50.35.bed.bed.list.out.num")
G4_2019.non_template.PDS.Q2_down_minus <- read_dist_table("./G4_seq_2019/exon.down_minus.q2.bed.score.GSM3003540_Homo_all_w15_th-1_minus.hits.max.PDS.w50.35.bed.bed.list.out.num")
G4_2019.non_template.PDS.Q3_down_minus <- read_dist_table("./G4_seq_2019/exon.down_minus.q3.bed.score.GSM3003540_Homo_all_w15_th-1_minus.hits.max.PDS.w50.35.bed.bed.list.out.num")
G4_2019.non_template.PDS.Q4_down_minus <- read_dist_table("./G4_seq_2019/exon.down_minus.q4.bed.score.GSM3003540_Homo_all_w15_th-1_minus.hits.max.PDS.w50.35.bed.bed.list.out.num")

G4_2019.template.PDS.Qs.plus.up.list <- list(G4_2019.template.PDS.Q1_up_plus, G4_2019.template.PDS.Q2_up_plus, G4_2019.template.PDS.Q3_up_plus, G4_2019.template.PDS.Q4_up_plus)
G4_2019.template.PDS.Qs.minus.list <- list(G4_2019.template.PDS.Q1_up_minus, G4_2019.template.PDS.Q2_up_minus, G4_2019.template.PDS.Q3_up_minus, G4_2019.template.PDS.Q4_up_minus)
G4_2019.template.PDS.Qs.plus.down.list <- list(G4_2019.template.PDS.Q1_down_plus, G4_2019.template.PDS.Q2_down_plus, G4_2019.template.PDS.Q3_down_plus, G4_2019.template.PDS.Q4_down_plus)
G4_2019.template.PDS.Qs.minus.down.list <- list(G4_2019.template.PDS.Q1_down_minus, G4_2019.template.PDS.Q2_down_minus, G4_2019.template.PDS.Q3_down_minus, G4_2019.template.PDS.Q4_down_minus)
G4_2019.template.PDS.window_len = 2000
G4_2019.template.PDS.Qs.total <- get_total_Qs(G4_2019.template.PDS.Qs.plus.up.list, G4_2019.template.PDS.Qs.minus.list, G4_2019.template.PDS.Qs.plus.down.list, G4_2019.template.PDS.Qs.minus.down.list, G4_2019.template.PDS.window_len)

G4_2019.non_template.PDS.Qs.plus.up.list <- list(G4_2019.non_template.PDS.Q1_up_plus, G4_2019.non_template.PDS.Q2_up_plus, G4_2019.non_template.PDS.Q3_up_plus, G4_2019.non_template.PDS.Q4_up_plus)
G4_2019.non_template.PDS.Qs.minus.list <- list(G4_2019.non_template.PDS.Q1_up_minus, G4_2019.non_template.PDS.Q2_up_minus, G4_2019.non_template.PDS.Q3_up_minus, G4_2019.non_template.PDS.Q4_up_minus)
G4_2019.non_template.PDS.Qs.plus.down.list <- list(G4_2019.non_template.PDS.Q1_down_plus, G4_2019.non_template.PDS.Q2_down_plus, G4_2019.non_template.PDS.Q3_down_plus, G4_2019.non_template.PDS.Q4_down_plus)
G4_2019.non_template.PDS.Qs.minus.down.list <- list(G4_2019.non_template.PDS.Q1_down_minus, G4_2019.non_template.PDS.Q2_down_minus, G4_2019.non_template.PDS.Q3_down_minus, G4_2019.non_template.PDS.Q4_down_minus)
G4_2019.non_template.PDS.window_len = 2000
G4_2019.non_template.PDS.Qs.total <- get_total_Qs(G4_2019.non_template.PDS.Qs.plus.up.list, G4_2019.non_template.PDS.Qs.minus.list, G4_2019.non_template.PDS.Qs.plus.down.list, G4_2019.non_template.PDS.Qs.minus.down.list, G4_2019.non_template.PDS.window_len)

G4_2019.template_non_template.PDS.Qs.total <- rbind(G4_2019.template.PDS.Qs.total, G4_2019.non_template.PDS.Qs.total)
  
half_n <- nrow(G4_2019.template_non_template.PDS.Qs.total)/2
G4_2019.template_non_template.PDS.Qs.total[, Strand:=rep(c("Template", "Non-template"), each=half_n) ]
  
  
  
  
G4_2019.template_non_template.PDS.Qs.total$Strand <-  factor(G4_2019.template_non_template.PDS.Qs.total$Strand, levels=c("Template", "Non-template" ))
  

G4_2019.template_non_template.PDS.Qs.total$Q <- mapvalues(G4_2019.template_non_template.PDS.Qs.total$Q,  from =c(1:4), to =c("Q1", "Q2", "Q3", "Q4"))
ggplot(G4_2019.template_non_template.PDS.Qs.total)+
  geom_line(aes(x=Position,y=Enrrichment, colour=Q)) +
  xlim(c(-150,150)) +
  facet_grid( Strand ~ exon_pos ) +
  labs(colour = "Splice site stregth quartile") +
  theme_bw()  + 
  theme(legend.position = "top", legend.direction = "horizontal")

G4_2019.template_non_template.PDS.Qs.total[Strand=="Non-template" , new_Strand:="Template"]
G4_2019.template_non_template.PDS.Qs.total[Strand=="Template" , new_Strand:="Non-template"]
  
G4_2019.template_non_template.PDS.Qs.total$new_Strand <-  factor(G4_2019.template_non_template.PDS.Qs.total$new_Strand, levels=c("Template", "Non-template" ))
ggplot(G4_2019.template_non_template.PDS.Qs.total)+
  geom_line(aes(x=Position,y=Enrrichment, colour=Q)) +
  xlim(c(-150,150)) +
  facet_grid( new_Strand ~ exon_pos ) +
  labs(colour = "Splice site stregth quartile") +
  theme_bw()  + 
  theme(legend.position = "top", legend.direction = "horizontal")

G4_2019.template.K.Q1_up_plus <- read_dist_table("./G4_seq_2019/exon.up_plus.q1.bed.score.GSM3003539_Homo_all_w15_th-1_minus.hits.max.K.w50.25.bed.bed.list.out.num")
G4_2019.template.K.Q2_up_plus <- read_dist_table("./G4_seq_2019/exon.up_plus.q2.bed.score.GSM3003539_Homo_all_w15_th-1_minus.hits.max.K.w50.25.bed.bed.list.out.num")
G4_2019.template.K.Q3_up_plus <- read_dist_table("./G4_seq_2019/exon.up_plus.q3.bed.score.GSM3003539_Homo_all_w15_th-1_minus.hits.max.K.w50.25.bed.bed.list.out.num")
G4_2019.template.K.Q4_up_plus <- read_dist_table("./G4_seq_2019/exon.up_plus.q4.bed.score.GSM3003539_Homo_all_w15_th-1_minus.hits.max.K.w50.25.bed.bed.list.out.num")
G4_2019.template.K.Q1_up_minus <- read_dist_table("./G4_seq_2019/exon.up_minus.q1.bed.score.GSM3003539_Homo_all_w15_th-1_plus.hits.max.K.w50.25.bed.bed.list.out.num")
G4_2019.template.K.Q2_up_minus <- read_dist_table("./G4_seq_2019/exon.up_minus.q2.bed.score.GSM3003539_Homo_all_w15_th-1_plus.hits.max.K.w50.25.bed.bed.list.out.num")
G4_2019.template.K.Q3_up_minus <- read_dist_table("./G4_seq_2019/exon.up_minus.q3.bed.score.GSM3003539_Homo_all_w15_th-1_plus.hits.max.K.w50.25.bed.bed.list.out.num")
G4_2019.template.K.Q4_up_minus <- read_dist_table("./G4_seq_2019/exon.up_minus.q4.bed.score.GSM3003539_Homo_all_w15_th-1_plus.hits.max.K.w50.25.bed.bed.list.out.num")
G4_2019.non_template.K.Q1_up_plus <- read_dist_table("./G4_seq_2019/exon.up_plus.q1.bed.score.GSM3003539_Homo_all_w15_th-1_plus.hits.max.K.w50.25.bed.bed.list.out.num")
G4_2019.non_template.K.Q2_up_plus <- read_dist_table("./G4_seq_2019/exon.up_plus.q2.bed.score.GSM3003539_Homo_all_w15_th-1_plus.hits.max.K.w50.25.bed.bed.list.out.num")
G4_2019.non_template.K.Q3_up_plus <- read_dist_table("./G4_seq_2019/exon.up_plus.q3.bed.score.GSM3003539_Homo_all_w15_th-1_plus.hits.max.K.w50.25.bed.bed.list.out.num")
G4_2019.non_template.K.Q4_up_plus <- read_dist_table("./G4_seq_2019/exon.up_plus.q4.bed.score.GSM3003539_Homo_all_w15_th-1_plus.hits.max.K.w50.25.bed.bed.list.out.num")
G4_2019.non_template.K.Q1_up_minus <- read_dist_table("./G4_seq_2019/exon.up_minus.q1.bed.score.GSM3003539_Homo_all_w15_th-1_minus.hits.max.K.w50.25.bed.bed.list.out.num")
G4_2019.non_template.K.Q2_up_minus <- read_dist_table("./G4_seq_2019/exon.up_minus.q2.bed.score.GSM3003539_Homo_all_w15_th-1_minus.hits.max.K.w50.25.bed.bed.list.out.num")
G4_2019.non_template.K.Q3_up_minus <- read_dist_table("./G4_seq_2019/exon.up_minus.q3.bed.score.GSM3003539_Homo_all_w15_th-1_minus.hits.max.K.w50.25.bed.bed.list.out.num")
G4_2019.non_template.K.Q4_up_minus <- read_dist_table("./G4_seq_2019/exon.up_minus.q4.bed.score.GSM3003539_Homo_all_w15_th-1_minus.hits.max.K.w50.25.bed.bed.list.out.num")
G4_2019.template.K.Q1_down_plus <- read_dist_table("./G4_seq_2019/exon.down_plus.q1.bed.score.GSM3003539_Homo_all_w15_th-1_minus.hits.max.K.w50.25.bed.bed.list.out.num")
G4_2019.template.K.Q2_down_plus <- read_dist_table("./G4_seq_2019/exon.down_plus.q2.bed.score.GSM3003539_Homo_all_w15_th-1_minus.hits.max.K.w50.25.bed.bed.list.out.num")
G4_2019.template.K.Q3_down_plus <- read_dist_table("./G4_seq_2019/exon.down_plus.q3.bed.score.GSM3003539_Homo_all_w15_th-1_minus.hits.max.K.w50.25.bed.bed.list.out.num")
G4_2019.template.K.Q4_down_plus <- read_dist_table("./G4_seq_2019/exon.down_plus.q4.bed.score.GSM3003539_Homo_all_w15_th-1_minus.hits.max.K.w50.25.bed.bed.list.out.num")
G4_2019.template.K.Q1_down_minus <- read_dist_table("./G4_seq_2019/exon.down_minus.q1.bed.score.GSM3003539_Homo_all_w15_th-1_plus.hits.max.K.w50.25.bed.bed.list.out.num")
G4_2019.template.K.Q2_down_minus <- read_dist_table("./G4_seq_2019/exon.down_minus.q2.bed.score.GSM3003539_Homo_all_w15_th-1_plus.hits.max.K.w50.25.bed.bed.list.out.num")
G4_2019.template.K.Q3_down_minus <- read_dist_table("./G4_seq_2019/exon.down_minus.q3.bed.score.GSM3003539_Homo_all_w15_th-1_plus.hits.max.K.w50.25.bed.bed.list.out.num")
G4_2019.template.K.Q4_down_minus <- read_dist_table("./G4_seq_2019/exon.down_minus.q4.bed.score.GSM3003539_Homo_all_w15_th-1_plus.hits.max.K.w50.25.bed.bed.list.out.num")
G4_2019.non_template.K.Q1_down_plus <- read_dist_table("./G4_seq_2019/exon.down_plus.q1.bed.score.GSM3003539_Homo_all_w15_th-1_plus.hits.max.K.w50.25.bed.bed.list.out.num")
G4_2019.non_template.K.Q2_down_plus <- read_dist_table("./G4_seq_2019/exon.down_plus.q2.bed.score.GSM3003539_Homo_all_w15_th-1_plus.hits.max.K.w50.25.bed.bed.list.out.num")
G4_2019.non_template.K.Q3_down_plus <- read_dist_table("./G4_seq_2019/exon.down_plus.q3.bed.score.GSM3003539_Homo_all_w15_th-1_plus.hits.max.K.w50.25.bed.bed.list.out.num")
G4_2019.non_template.K.Q4_down_plus <- read_dist_table("./G4_seq_2019/exon.down_plus.q4.bed.score.GSM3003539_Homo_all_w15_th-1_plus.hits.max.K.w50.25.bed.bed.list.out.num")
G4_2019.non_template.K.Q1_down_minus <- read_dist_table("./G4_seq_2019/exon.down_minus.q1.bed.score.GSM3003539_Homo_all_w15_th-1_minus.hits.max.K.w50.25.bed.bed.list.out.num")
G4_2019.non_template.K.Q2_down_minus <- read_dist_table("./G4_seq_2019/exon.down_minus.q2.bed.score.GSM3003539_Homo_all_w15_th-1_minus.hits.max.K.w50.25.bed.bed.list.out.num")
G4_2019.non_template.K.Q3_down_minus <- read_dist_table("./G4_seq_2019/exon.down_minus.q3.bed.score.GSM3003539_Homo_all_w15_th-1_minus.hits.max.K.w50.25.bed.bed.list.out.num")
G4_2019.non_template.K.Q4_down_minus <- read_dist_table("./G4_seq_2019/exon.down_minus.q4.bed.score.GSM3003539_Homo_all_w15_th-1_minus.hits.max.K.w50.25.bed.bed.list.out.num")

G4_2019.template.K.Qs.plus.up.list <- list(G4_2019.template.K.Q1_up_plus, G4_2019.template.K.Q2_up_plus, G4_2019.template.K.Q3_up_plus, G4_2019.template.K.Q4_up_plus)
G4_2019.template.K.Qs.minus.list <- list(G4_2019.template.K.Q1_up_minus, G4_2019.template.K.Q2_up_minus, G4_2019.template.K.Q3_up_minus, G4_2019.template.K.Q4_up_minus)
G4_2019.template.K.Qs.plus.down.list <- list(G4_2019.template.K.Q1_down_plus, G4_2019.template.K.Q2_down_plus, G4_2019.template.K.Q3_down_plus, G4_2019.template.K.Q4_down_plus)
G4_2019.template.K.Qs.minus.down.list <- list(G4_2019.template.K.Q1_down_minus, G4_2019.template.K.Q2_down_minus, G4_2019.template.K.Q3_down_minus, G4_2019.template.K.Q4_down_minus)
G4_2019.template.K.window_len = 2000
G4_2019.template.K.Qs.total <- get_total_Qs(G4_2019.template.K.Qs.plus.up.list, G4_2019.template.K.Qs.minus.list, G4_2019.template.K.Qs.plus.down.list, G4_2019.template.K.Qs.minus.down.list, G4_2019.template.K.window_len)

G4_2019.non_template.K.Qs.plus.up.list <- list(G4_2019.non_template.K.Q1_up_plus, G4_2019.non_template.K.Q2_up_plus, G4_2019.non_template.K.Q3_up_plus, G4_2019.non_template.K.Q4_up_plus)
G4_2019.non_template.K.Qs.minus.list <- list(G4_2019.non_template.K.Q1_up_minus, G4_2019.non_template.K.Q2_up_minus, G4_2019.non_template.K.Q3_up_minus, G4_2019.non_template.K.Q4_up_minus)
G4_2019.non_template.K.Qs.plus.down.list <- list(G4_2019.non_template.K.Q1_down_plus, G4_2019.non_template.K.Q2_down_plus, G4_2019.non_template.K.Q3_down_plus, G4_2019.non_template.K.Q4_down_plus)
G4_2019.non_template.K.Qs.minus.down.list <- list(G4_2019.non_template.K.Q1_down_minus, G4_2019.non_template.K.Q2_down_minus, G4_2019.non_template.K.Q3_down_minus, G4_2019.non_template.K.Q4_down_minus)
G4_2019.non_template.K.window_len = 2000
G4_2019.non_template.K.Qs.total <- get_total_Qs(G4_2019.non_template.K.Qs.plus.up.list, G4_2019.non_template.K.Qs.minus.list, G4_2019.non_template.K.Qs.plus.down.list, G4_2019.non_template.K.Qs.minus.down.list, G4_2019.non_template.K.window_len)

G4_2019.template.K.Qs.total

       Position Q Occurrences.x median.x Enrrichment.x Occurrences.y median.y Enrrichment.y Occurrences median Enrrichment   exon_pos
    1:    -1000 1           825    903.0     0.9136213           840      854     0.9836066        1665   1741   0.9563469   Upstream
    2:    -1000 2           673    716.0     0.9399441           638      684     0.9327485        1311   1408   0.9311080   Upstream
    3:    -1000 3           555    567.0     0.9788360           592      546     1.0842491        1147   1116   1.0277778   Upstream
    4:    -1000 4           413    370.0     1.1162162           364      370     0.9837838         777    749   1.0373832   Upstream
    5:     -999 1           833    903.0     0.9224806           845      854     0.9894614        1678   1741   0.9638139   Upstream
   ---                                                                                                                               
15988:      997 4           480    540.0     0.8888889           474      540     0.8777778         954   1093   0.8728271 Downstream
15989:      998 1           579    698.0     0.8295129           561      640     0.8765625        1140   1347   0.8463252 Downstream
15990:      998 2           560    680.0     0.8235294           527      657     0.8021309        1087   1334   0.8148426 Downstream
15991:      998 3           504    590.5     0.8535140           472      595     0.7932773         976   1192   0.8187919 Downstream
15992:      998 4           484    540.0     0.8962963           474      540     0.8777778         958   1093   0.8764867 Downstream

G4_2019.non_template.K.Qs.total

       Position Q Occurrences.x median.x Enrrichment.x Occurrences.y median.y Enrrichment.y Occurrences median Enrrichment   exon_pos
    1:    -1000 1           682      749     0.9105474           697      726     0.9600551        1379   1471   0.9374575   Upstream
    2:    -1000 2           564      618     0.9126214           573      594     0.9646465        1137   1212   0.9381188   Upstream
    3:    -1000 3           455      469     0.9701493           455      450     1.0111111         910    920   0.9891304   Upstream
    4:    -1000 4           339      341     0.9941349           345      324     1.0648148         684    665   1.0285714   Upstream
    5:     -999 1           685      749     0.9145527           695      726     0.9573003        1380   1471   0.9381373   Upstream
   ---                                                                                                                               
15988:      997 4           475      505     0.9405941           453      471     0.9617834         928    969   0.9576883 Downstream
15989:      998 1           614      600     1.0233333           494      558     0.8853047        1108   1151   0.9626412 Downstream
15990:      998 2           553      567     0.9753086           542      548     0.9890511        1095   1113   0.9838275 Downstream
15991:      998 3           530      523     1.0133843           461      494     0.9331984         991   1014   0.9773176 Downstream
15992:      998 4           474      505     0.9386139           456      471     0.9681529         930    969   0.9597523 Downstream

G4_2019.template_non_template.K.Qs.total <- rbind(G4_2019.template.K.Qs.total, G4_2019.non_template.K.Qs.total)
  
half_n <- nrow(G4_2019.template_non_template.K.Qs.total)/2
G4_2019.template_non_template.K.Qs.total[, Strand:=rep(c("Template", "Non-template"), each=half_n) ]
  
  
  
  
G4_2019.template_non_template.K.Qs.total$Strand <-  factor(G4_2019.template_non_template.K.Qs.total$Strand, levels=c("Template", "Non-template" ))
  

G4_2019.template_non_template.K.Qs.total$Q <- mapvalues(G4_2019.template_non_template.K.Qs.total$Q,  from =c(1:4), to =c("Q1", "Q2", "Q3", "Q4"))
G4_2019.template_non_template.K.Qs.total[Strand=="Non-template" , new_Strand:="Template"]
G4_2019.template_non_template.K.Qs.total[Strand=="Template" , new_Strand:="Non-template"]
G4_2019.template_non_template.K.Qs.total$new_Strand <-  factor(G4_2019.template_non_template.K.Qs.total$new_Strand, levels=c("Template", "Non-template" ))
ggplot(G4_2019.template_non_template.K.Qs.total)+
  geom_line(aes(x=Position,y=Enrrichment, colour=Q)) +
  xlim(c(-150,150)) +
  facet_grid( new_Strand ~ exon_pos ) +
  labs(colour = "Splice site stregth quartile") +
  theme_bw()  + 
  theme(legend.position = "top", legend.direction = "horizontal")

#2015
G4_2015.Na_PDS.Q1_up_plus <- read_dist_table("./G4_seq_2015/exon.up_plus.q1.bed.score.GSE63874_Na_PDS_plus_minus_hits_intersect.bed.bed.list.out.num")
G4_2015.Na_PDS.Q2_up_plus <- read_dist_table("./G4_seq_2015/exon.up_plus.q2.bed.score.GSE63874_Na_PDS_plus_minus_hits_intersect.bed.bed.list.out.num")
G4_2015.Na_PDS.Q3_up_plus <- read_dist_table("./G4_seq_2015/exon.up_plus.q3.bed.score.GSE63874_Na_PDS_plus_minus_hits_intersect.bed.bed.list.out.num")
G4_2015.Na_PDS.Q4_up_plus <- read_dist_table("./G4_seq_2015/exon.up_plus.q4.bed.score.GSE63874_Na_PDS_plus_minus_hits_intersect.bed.bed.list.out.num")
G4_2015.Na_PDS.Q1_up_minus <- read_dist_table("./G4_seq_2015/exon.up_minus.q1.bed.score.GSE63874_Na_PDS_plus_minus_hits_intersect.bed.bed.list.out.num")
G4_2015.Na_PDS.Q2_up_minus <- read_dist_table("./G4_seq_2015/exon.up_minus.q2.bed.score.GSE63874_Na_PDS_plus_minus_hits_intersect.bed.bed.list.out.num")
G4_2015.Na_PDS.Q3_up_minus <- read_dist_table("./G4_seq_2015/exon.up_minus.q3.bed.score.GSE63874_Na_PDS_plus_minus_hits_intersect.bed.bed.list.out.num")
G4_2015.Na_PDS.Q4_up_minus <- read_dist_table("./G4_seq_2015/exon.up_minus.q4.bed.score.GSE63874_Na_PDS_plus_minus_hits_intersect.bed.bed.list.out.num")
G4_2015.Na_PDS.Q1_down_plus <- read_dist_table("./G4_seq_2015/exon.down_plus.q1.bed.score.GSE63874_Na_PDS_plus_minus_hits_intersect.bed.bed.list.out.num")
G4_2015.Na_PDS.Q2_down_plus <- read_dist_table("./G4_seq_2015/exon.down_plus.q2.bed.score.GSE63874_Na_PDS_plus_minus_hits_intersect.bed.bed.list.out.num")
G4_2015.Na_PDS.Q3_down_plus <- read_dist_table("./G4_seq_2015/exon.down_plus.q3.bed.score.GSE63874_Na_PDS_plus_minus_hits_intersect.bed.bed.list.out.num")
G4_2015.Na_PDS.Q4_down_plus <- read_dist_table("./G4_seq_2015/exon.down_plus.q4.bed.score.GSE63874_Na_PDS_plus_minus_hits_intersect.bed.bed.list.out.num")
G4_2015.Na_PDS.Q1_down_minus <- read_dist_table("./G4_seq_2015/exon.down_minus.q1.bed.score.GSE63874_Na_PDS_plus_minus_hits_intersect.bed.bed.list.out.num")
G4_2015.Na_PDS.Q2_down_minus <- read_dist_table("./G4_seq_2015/exon.down_minus.q2.bed.score.GSE63874_Na_PDS_plus_minus_hits_intersect.bed.bed.list.out.num")
G4_2015.Na_PDS.Q3_down_minus <- read_dist_table("./G4_seq_2015/exon.down_minus.q3.bed.score.GSE63874_Na_PDS_plus_minus_hits_intersect.bed.bed.list.out.num")
G4_2015.Na_PDS.Q4_down_minus <- read_dist_table("./G4_seq_2015/exon.down_minus.q4.bed.score.GSE63874_Na_PDS_plus_minus_hits_intersect.bed.bed.list.out.num")
G4_2015.Na_PDS.Qs.plus.up.list <- list(G4_2015.Na_PDS.Q1_up_plus, G4_2015.Na_PDS.Q2_up_plus, G4_2015.Na_PDS.Q3_up_plus, G4_2015.Na_PDS.Q4_up_plus)
G4_2015.Na_PDS.Qs.minus.list <- list(G4_2015.Na_PDS.Q1_up_minus, G4_2015.Na_PDS.Q2_up_minus, G4_2015.Na_PDS.Q3_up_minus, G4_2015.Na_PDS.Q4_up_minus)
G4_2015.Na_PDS.Qs.plus.down.list <- list(G4_2015.Na_PDS.Q1_down_plus, G4_2015.Na_PDS.Q2_down_plus, G4_2015.Na_PDS.Q3_down_plus, G4_2015.Na_PDS.Q4_down_plus)
G4_2015.Na_PDS.Qs.minus.down.list <- list(G4_2015.Na_PDS.Q1_down_minus, G4_2015.Na_PDS.Q2_down_minus, G4_2015.Na_PDS.Q3_down_minus, G4_2015.Na_PDS.Q4_down_minus)
G4_2015.Na_PDS.window_len = 2000
G4_2015.Na_PDS.Qs.total <- get_total_Qs(G4_2015.Na_PDS.Qs.plus.up.list, G4_2015.Na_PDS.Qs.minus.list, G4_2015.Na_PDS.Qs.plus.down.list, G4_2015.Na_PDS.Qs.minus.down.list, G4_2015.Na_PDS.window_len)
ggplot(G4_2015.Na_PDS.Qs.total)+
  geom_line(aes(x=Position,y=Enrrichment, colour=Q)) +
  xlim(c(-200,200)) +
  facet_grid( . ~ exon_pos ) +
  theme(text = element_text(size=15)) +
  theme_bw() + 
  labs(colour = "Splice site stregth quartile") +
  theme(legend.position = "top", legend.direction = "horizontal")

G4_2015.Na_K.Q1_up_plus <- read_dist_table("./G4_seq_2015/exon.up_plus.q1.bed.score.GSE63874_Na_K_plus_minus_hits_intersect.bed.bed.list.out.num")
G4_2015.Na_K.Q2_up_plus <- read_dist_table("./G4_seq_2015/exon.up_plus.q2.bed.score.GSE63874_Na_K_plus_minus_hits_intersect.bed.bed.list.out.num")
G4_2015.Na_K.Q3_up_plus <- read_dist_table("./G4_seq_2015/exon.up_plus.q3.bed.score.GSE63874_Na_K_plus_minus_hits_intersect.bed.bed.list.out.num")
G4_2015.Na_K.Q4_up_plus <- read_dist_table("./G4_seq_2015/exon.up_plus.q4.bed.score.GSE63874_Na_K_plus_minus_hits_intersect.bed.bed.list.out.num")
G4_2015.Na_K.Q1_up_minus <- read_dist_table("./G4_seq_2015/exon.up_minus.q1.bed.score.GSE63874_Na_K_plus_minus_hits_intersect.bed.bed.list.out.num")
G4_2015.Na_K.Q2_up_minus <- read_dist_table("./G4_seq_2015/exon.up_minus.q2.bed.score.GSE63874_Na_K_plus_minus_hits_intersect.bed.bed.list.out.num")
G4_2015.Na_K.Q3_up_minus <- read_dist_table("./G4_seq_2015/exon.up_minus.q3.bed.score.GSE63874_Na_K_plus_minus_hits_intersect.bed.bed.list.out.num")
G4_2015.Na_K.Q4_up_minus <- read_dist_table("./G4_seq_2015/exon.up_minus.q4.bed.score.GSE63874_Na_K_plus_minus_hits_intersect.bed.bed.list.out.num")
G4_2015.Na_K.Q1_down_plus <- read_dist_table("./G4_seq_2015/exon.down_plus.q1.bed.score.GSE63874_Na_K_plus_minus_hits_intersect.bed.bed.list.out.num")
G4_2015.Na_K.Q2_down_plus <- read_dist_table("./G4_seq_2015/exon.down_plus.q2.bed.score.GSE63874_Na_K_plus_minus_hits_intersect.bed.bed.list.out.num")
G4_2015.Na_K.Q3_down_plus <- read_dist_table("./G4_seq_2015/exon.down_plus.q3.bed.score.GSE63874_Na_K_plus_minus_hits_intersect.bed.bed.list.out.num")
G4_2015.Na_K.Q4_down_plus <- read_dist_table("./G4_seq_2015/exon.down_plus.q4.bed.score.GSE63874_Na_K_plus_minus_hits_intersect.bed.bed.list.out.num")
G4_2015.Na_K.Q1_down_minus <- read_dist_table("./G4_seq_2015/exon.down_minus.q1.bed.score.GSE63874_Na_K_plus_minus_hits_intersect.bed.bed.list.out.num")
G4_2015.Na_K.Q2_down_minus <- read_dist_table("./G4_seq_2015/exon.down_minus.q2.bed.score.GSE63874_Na_K_plus_minus_hits_intersect.bed.bed.list.out.num")
G4_2015.Na_K.Q3_down_minus <- read_dist_table("./G4_seq_2015/exon.down_minus.q3.bed.score.GSE63874_Na_K_plus_minus_hits_intersect.bed.bed.list.out.num")
G4_2015.Na_K.Q4_down_minus <- read_dist_table("./G4_seq_2015/exon.down_minus.q4.bed.score.GSE63874_Na_K_plus_minus_hits_intersect.bed.bed.list.out.num")
G4_2015.Na_K.Qs.plus.up.list <- list(G4_2015.Na_K.Q1_up_plus, G4_2015.Na_K.Q2_up_plus, G4_2015.Na_K.Q3_up_plus, G4_2015.Na_K.Q4_up_plus)
G4_2015.Na_K.Qs.minus.list <- list(G4_2015.Na_K.Q1_up_minus, G4_2015.Na_K.Q2_up_minus, G4_2015.Na_K.Q3_up_minus, G4_2015.Na_K.Q4_up_minus)
G4_2015.Na_K.Qs.plus.down.list <- list(G4_2015.Na_K.Q1_down_plus, G4_2015.Na_K.Q2_down_plus, G4_2015.Na_K.Q3_down_plus, G4_2015.Na_K.Q4_down_plus)
G4_2015.Na_K.Qs.minus.down.list <- list(G4_2015.Na_K.Q1_down_minus, G4_2015.Na_K.Q2_down_minus, G4_2015.Na_K.Q3_down_minus, G4_2015.Na_K.Q4_down_minus)
G4_2015.Na_K.window_len = 2000
G4_2015.Na_K.Qs.total <- get_total_Qs(G4_2015.Na_K.Qs.plus.up.list, G4_2015.Na_K.Qs.minus.list, G4_2015.Na_K.Qs.plus.down.list, G4_2015.Na_K.Qs.minus.down.list, G4_2015.Na_K.window_len)
ggplot(G4_2015.Na_K.Qs.total)+
  geom_line(aes(x=Position,y=Enrrichment, colour=Q)) +
  xlim(c(-200,200)) +
  facet_grid( . ~ exon_pos ) +
  theme(text = element_text(size=15)) +
  theme_bw() + 
  labs(colour = "Splice site stregth quartile") +
  theme(legend.position = "top", legend.direction = "horizontal")

G4_2015.template.Na_PDS.Q1_up_plus <- read_dist_table("./G4_seq_2015/exon.up_plus.q1.bed.score.GSE63874_Na_PDS_minus_hits_intersect.bed.bed.list.out.num")
G4_2015.template.Na_PDS.Q2_up_plus <- read_dist_table("./G4_seq_2015/exon.up_plus.q2.bed.score.GSE63874_Na_PDS_minus_hits_intersect.bed.bed.list.out.num")
G4_2015.template.Na_PDS.Q3_up_plus <- read_dist_table("./G4_seq_2015/exon.up_plus.q3.bed.score.GSE63874_Na_PDS_minus_hits_intersect.bed.bed.list.out.num")
G4_2015.template.Na_PDS.Q4_up_plus <- read_dist_table("./G4_seq_2015/exon.up_plus.q4.bed.score.GSE63874_Na_PDS_minus_hits_intersect.bed.bed.list.out.num")
G4_2015.template.Na_PDS.Q1_up_minus <- read_dist_table("./G4_seq_2015/exon.up_minus.q1.bed.score.GSE63874_Na_PDS_plus_hits_intersect.bed.bed.list.out.num")
G4_2015.template.Na_PDS.Q2_up_minus <- read_dist_table("./G4_seq_2015/exon.up_minus.q2.bed.score.GSE63874_Na_PDS_plus_hits_intersect.bed.bed.list.out.num")
G4_2015.template.Na_PDS.Q3_up_minus <- read_dist_table("./G4_seq_2015/exon.up_minus.q3.bed.score.GSE63874_Na_PDS_plus_hits_intersect.bed.bed.list.out.num")
G4_2015.template.Na_PDS.Q4_up_minus <- read_dist_table("./G4_seq_2015/exon.up_minus.q4.bed.score.GSE63874_Na_PDS_plus_hits_intersect.bed.bed.list.out.num")
G4_2015.non_template.Na_PDS.Q1_up_plus <- read_dist_table("./G4_seq_2015/exon.up_plus.q1.bed.score.GSE63874_Na_PDS_plus_hits_intersect.bed.bed.list.out.num")
G4_2015.non_template.Na_PDS.Q2_up_plus <- read_dist_table("./G4_seq_2015/exon.up_plus.q2.bed.score.GSE63874_Na_PDS_plus_hits_intersect.bed.bed.list.out.num")
G4_2015.non_template.Na_PDS.Q3_up_plus <- read_dist_table("./G4_seq_2015/exon.up_plus.q3.bed.score.GSE63874_Na_PDS_plus_hits_intersect.bed.bed.list.out.num")
G4_2015.non_template.Na_PDS.Q4_up_plus <- read_dist_table("./G4_seq_2015/exon.up_plus.q4.bed.score.GSE63874_Na_PDS_plus_hits_intersect.bed.bed.list.out.num")
G4_2015.non_template.Na_PDS.Q1_up_minus <- read_dist_table("./G4_seq_2015/exon.up_minus.q1.bed.score.GSE63874_Na_PDS_minus_hits_intersect.bed.bed.list.out.num")
G4_2015.non_template.Na_PDS.Q2_up_minus <- read_dist_table("./G4_seq_2015/exon.up_minus.q2.bed.score.GSE63874_Na_PDS_minus_hits_intersect.bed.bed.list.out.num")
G4_2015.non_template.Na_PDS.Q3_up_minus <- read_dist_table("./G4_seq_2015/exon.up_minus.q3.bed.score.GSE63874_Na_PDS_minus_hits_intersect.bed.bed.list.out.num")
G4_2015.non_template.Na_PDS.Q4_up_minus <- read_dist_table("./G4_seq_2015/exon.up_minus.q4.bed.score.GSE63874_Na_PDS_minus_hits_intersect.bed.bed.list.out.num")
G4_2015.template.Na_PDS.Q1_down_plus <- read_dist_table("./G4_seq_2015/exon.down_plus.q1.bed.score.GSE63874_Na_PDS_minus_hits_intersect.bed.bed.list.out.num")
G4_2015.template.Na_PDS.Q2_down_plus <- read_dist_table("./G4_seq_2015/exon.down_plus.q2.bed.score.GSE63874_Na_PDS_minus_hits_intersect.bed.bed.list.out.num")
G4_2015.template.Na_PDS.Q3_down_plus <- read_dist_table("./G4_seq_2015/exon.down_plus.q3.bed.score.GSE63874_Na_PDS_minus_hits_intersect.bed.bed.list.out.num")
G4_2015.template.Na_PDS.Q4_down_plus <- read_dist_table("./G4_seq_2015/exon.down_plus.q4.bed.score.GSE63874_Na_PDS_minus_hits_intersect.bed.bed.list.out.num")
G4_2015.template.Na_PDS.Q1_down_minus <- read_dist_table("./G4_seq_2015/exon.down_minus.q1.bed.score.GSE63874_Na_PDS_plus_hits_intersect.bed.bed.list.out.num")
G4_2015.template.Na_PDS.Q2_down_minus <- read_dist_table("./G4_seq_2015/exon.down_minus.q2.bed.score.GSE63874_Na_PDS_plus_hits_intersect.bed.bed.list.out.num")
G4_2015.template.Na_PDS.Q3_down_minus <- read_dist_table("./G4_seq_2015/exon.down_minus.q3.bed.score.GSE63874_Na_PDS_plus_hits_intersect.bed.bed.list.out.num")
G4_2015.template.Na_PDS.Q4_down_minus <- read_dist_table("./G4_seq_2015/exon.down_minus.q4.bed.score.GSE63874_Na_PDS_plus_hits_intersect.bed.bed.list.out.num")
G4_2015.non_template.Na_PDS.Q1_down_plus <- read_dist_table("./G4_seq_2015/exon.down_plus.q1.bed.score.GSE63874_Na_PDS_plus_hits_intersect.bed.bed.list.out.num")
G4_2015.non_template.Na_PDS.Q2_down_plus <- read_dist_table("./G4_seq_2015/exon.down_plus.q2.bed.score.GSE63874_Na_PDS_plus_hits_intersect.bed.bed.list.out.num")
G4_2015.non_template.Na_PDS.Q3_down_plus <- read_dist_table("./G4_seq_2015/exon.down_plus.q3.bed.score.GSE63874_Na_PDS_plus_hits_intersect.bed.bed.list.out.num")
G4_2015.non_template.Na_PDS.Q4_down_plus <- read_dist_table("./G4_seq_2015/exon.down_plus.q4.bed.score.GSE63874_Na_PDS_plus_hits_intersect.bed.bed.list.out.num")
G4_2015.non_template.Na_PDS.Q1_down_minus <- read_dist_table("./G4_seq_2015/exon.down_minus.q1.bed.score.GSE63874_Na_PDS_minus_hits_intersect.bed.bed.list.out.num")
G4_2015.non_template.Na_PDS.Q2_down_minus <- read_dist_table("./G4_seq_2015/exon.down_minus.q2.bed.score.GSE63874_Na_PDS_minus_hits_intersect.bed.bed.list.out.num")
G4_2015.non_template.Na_PDS.Q3_down_minus <- read_dist_table("./G4_seq_2015/exon.down_minus.q3.bed.score.GSE63874_Na_PDS_minus_hits_intersect.bed.bed.list.out.num")
G4_2015.non_template.Na_PDS.Q4_down_minus <- read_dist_table("./G4_seq_2015/exon.down_minus.q4.bed.score.GSE63874_Na_PDS_minus_hits_intersect.bed.bed.list.out.num")

G4_2015.template.Na_PDS.Qs.plus.up.list <- list(G4_2015.template.Na_PDS.Q1_up_plus, G4_2015.template.Na_PDS.Q2_up_plus, G4_2015.template.Na_PDS.Q3_up_plus, G4_2015.template.Na_PDS.Q4_up_plus)
G4_2015.template.Na_PDS.Qs.minus.list <- list(G4_2015.template.Na_PDS.Q1_up_minus, G4_2015.template.Na_PDS.Q2_up_minus, G4_2015.template.Na_PDS.Q3_up_minus, G4_2015.template.Na_PDS.Q4_up_minus)
G4_2015.template.Na_PDS.Qs.plus.down.list <- list(G4_2015.template.Na_PDS.Q1_down_plus, G4_2015.template.Na_PDS.Q2_down_plus, G4_2015.template.Na_PDS.Q3_down_plus, G4_2015.template.Na_PDS.Q4_down_plus)
G4_2015.template.Na_PDS.Qs.minus.down.list <- list(G4_2015.template.Na_PDS.Q1_down_minus, G4_2015.template.Na_PDS.Q2_down_minus, G4_2015.template.Na_PDS.Q3_down_minus, G4_2015.template.Na_PDS.Q4_down_minus)
G4_2015.template.Na_PDS.window_len = 2000
G4_2015.template.Na_PDS.Qs.total <- get_total_Qs(G4_2015.template.Na_PDS.Qs.plus.up.list, G4_2015.template.Na_PDS.Qs.minus.list, G4_2015.template.Na_PDS.Qs.plus.down.list, G4_2015.template.Na_PDS.Qs.minus.down.list, G4_2015.template.Na_PDS.window_len)

G4_2015.non_template.Na_PDS.Qs.plus.up.list <- list(G4_2015.non_template.Na_PDS.Q1_up_plus, G4_2015.non_template.Na_PDS.Q2_up_plus, G4_2015.non_template.Na_PDS.Q3_up_plus, G4_2015.non_template.Na_PDS.Q4_up_plus)
G4_2015.non_template.Na_PDS.Qs.minus.list <- list(G4_2015.non_template.Na_PDS.Q1_up_minus, G4_2015.non_template.Na_PDS.Q2_up_minus, G4_2015.non_template.Na_PDS.Q3_up_minus, G4_2015.non_template.Na_PDS.Q4_up_minus)
G4_2015.non_template.Na_PDS.Qs.plus.down.list <- list(G4_2015.non_template.Na_PDS.Q1_down_plus, G4_2015.non_template.Na_PDS.Q2_down_plus, G4_2015.non_template.Na_PDS.Q3_down_plus, G4_2015.non_template.Na_PDS.Q4_down_plus)
G4_2015.non_template.Na_PDS.Qs.minus.down.list <- list(G4_2015.non_template.Na_PDS.Q1_down_minus, G4_2015.non_template.Na_PDS.Q2_down_minus, G4_2015.non_template.Na_PDS.Q3_down_minus, G4_2015.non_template.Na_PDS.Q4_down_minus)
G4_2015.non_template.Na_PDS.window_len = 2000
G4_2015.non_template.Na_PDS.Qs.total <- get_total_Qs(G4_2015.non_template.Na_PDS.Qs.plus.up.list, G4_2015.non_template.Na_PDS.Qs.minus.list, G4_2015.non_template.Na_PDS.Qs.plus.down.list, G4_2015.non_template.Na_PDS.Qs.minus.down.list, G4_2015.non_template.Na_PDS.window_len)

G4_2015.template.Na_PDS.Qs.total

       Position Q Occurrences.x median.x Enrrichment.x Occurrences.y median.y Enrrichment.y Occurrences median Enrrichment   exon_pos
    1:    -1000 1          3230     3421     0.9441684          3119   3238.5     0.9631002        6349   6677   0.9508761   Upstream
    2:    -1000 2          2693     2711     0.9933604          2396   2540.0     0.9433071        5089   5232   0.9726682   Upstream
    3:    -1000 3          1991     1997     0.9969955          1927   1975.0     0.9756962        3918   3998   0.9799900   Upstream
    4:    -1000 4          1455     1331     1.0931630          1357   1287.0     1.0543901        2812   2635   1.0671727   Upstream
    5:     -999 1          3244     3421     0.9482607          3112   3238.5     0.9609387        6356   6677   0.9519245   Upstream
   ---                                                                                                                               
15988:      997 4          1716     2058     0.8338192          1686   2051.0     0.8220380        3402   4144   0.8209459 Downstream
15989:      998 1          2169     2586     0.8387471          2143   2386.0     0.8981559        4312   4961   0.8691796 Downstream
15990:      998 2          2130     2578     0.8262219          1926   2395.0     0.8041754        4056   4983   0.8139675 Downstream
15991:      998 3          1854     2200     0.8427273          1865   2153.0     0.8662332        3719   4357   0.8535690 Downstream
15992:      998 4          1716     2058     0.8338192          1684   2051.0     0.8210629        3400   4144   0.8204633 Downstream

G4_2015.non_template.Na_PDS.Qs.total

       Position Q Occurrences.x median.x Enrrichment.x Occurrences.y median.y Enrrichment.y Occurrences median Enrrichment   exon_pos
    1:    -1000 1          2746   2794.0     0.9828203          2528   2744.0     0.9212828        5274   5538   0.9523294   Upstream
    2:    -1000 2          2178   2259.0     0.9641434          1987   2130.0     0.9328638        4165   4378   0.9513476   Upstream
    3:    -1000 3          1591   1697.0     0.9375368          1566   1590.0     0.9849057        3157   3266   0.9666258   Upstream
    4:    -1000 4          1190   1162.0     1.0240964          1095   1068.0     1.0252809        2285   2223   1.0278902   Upstream
    5:     -999 1          2736   2794.0     0.9792412          2533   2744.0     0.9231050        5269   5538   0.9514265   Upstream
   ---                                                                                                                               
15988:      997 4          1671   1744.0     0.9581422          1540   1686.0     0.9134045        3211   3394   0.9460813 Downstream
15989:      998 1          2109   2196.0     0.9603825          1862   2021.0     0.9213261        3971   4204   0.9445766 Downstream
15990:      998 2          1996   2118.5     0.9421761          1846   2024.5     0.9118301        3842   4140   0.9280193 Downstream
15991:      998 3          1793   1857.0     0.9655358          1733   1799.0     0.9633130        3526   3665   0.9620737 Downstream
15992:      998 4          1672   1744.0     0.9587156          1545   1686.0     0.9163701        3217   3394   0.9478491 Downstream

G4_2015.template_non_template.Na_PDS.Qs.total <- rbind(G4_2015.template.Na_PDS.Qs.total, G4_2015.non_template.Na_PDS.Qs.total)
  
half_n <- nrow(G4_2015.template_non_template.Na_PDS.Qs.total)/2
G4_2015.template_non_template.Na_PDS.Qs.total[, Strand:=rep(c("Template", "Non-template"), each=half_n) ]
  
  
  
  
G4_2015.template_non_template.Na_PDS.Qs.total$Strand <-  factor(G4_2015.template_non_template.Na_PDS.Qs.total$Strand, levels=c("Template", "Non-template" ))
  

G4_2015.template_non_template.Na_PDS.Qs.total$Q <- mapvalues(G4_2015.template_non_template.Na_PDS.Qs.total$Q,  from =c(1:4), to =c("Q1", "Q2", "Q3", "Q4"))
G4_2015.template_non_template.Na_PDS.Qs.total[Strand=="Non-template" , new_Strand:="Template"]
G4_2015.template_non_template.Na_PDS.Qs.total[Strand=="Template" , new_Strand:="Non-template"]
G4_2015.template_non_template.Na_PDS.Qs.total$new_Strand <-  factor(G4_2015.template_non_template.Na_PDS.Qs.total$new_Strand, levels=c("Template", "Non-template" ))
ggplot(G4_2015.template_non_template.Na_PDS.Qs.total)+
  geom_line(aes(x=Position,y=Enrrichment, colour=Q)) +
  xlim(c(-300,300)) +
  facet_grid( new_Strand ~ exon_pos ) +
  labs(colour = "Splice site stregth quartile") +
  theme_bw()  + 
  theme(legend.position = "top", legend.direction = "horizontal")

G4_2015.template.Na_K.Q1_up_plus <- read_dist_table("./G4_seq_2015/exon.up_plus.q1.bed.score.GSE63874_Na_K_minus_hits_intersect.bed.bed.list.out.num")
G4_2015.template.Na_K.Q2_up_plus <- read_dist_table("./G4_seq_2015/exon.up_plus.q2.bed.score.GSE63874_Na_K_minus_hits_intersect.bed.bed.list.out.num")
G4_2015.template.Na_K.Q3_up_plus <- read_dist_table("./G4_seq_2015/exon.up_plus.q3.bed.score.GSE63874_Na_K_minus_hits_intersect.bed.bed.list.out.num")
G4_2015.template.Na_K.Q4_up_plus <- read_dist_table("./G4_seq_2015/exon.up_plus.q4.bed.score.GSE63874_Na_K_minus_hits_intersect.bed.bed.list.out.num")
G4_2015.template.Na_K.Q1_up_minus <- read_dist_table("./G4_seq_2015/exon.up_minus.q1.bed.score.GSE63874_Na_K_plus_hits_intersect.bed.bed.list.out.num")
G4_2015.template.Na_K.Q2_up_minus <- read_dist_table("./G4_seq_2015/exon.up_minus.q2.bed.score.GSE63874_Na_K_plus_hits_intersect.bed.bed.list.out.num")
G4_2015.template.Na_K.Q3_up_minus <- read_dist_table("./G4_seq_2015/exon.up_minus.q3.bed.score.GSE63874_Na_K_plus_hits_intersect.bed.bed.list.out.num")
G4_2015.template.Na_K.Q4_up_minus <- read_dist_table("./G4_seq_2015/exon.up_minus.q4.bed.score.GSE63874_Na_K_plus_hits_intersect.bed.bed.list.out.num")
G4_2015.non_template.Na_K.Q1_up_plus <- read_dist_table("./G4_seq_2015/exon.up_plus.q1.bed.score.GSE63874_Na_K_plus_hits_intersect.bed.bed.list.out.num")
G4_2015.non_template.Na_K.Q2_up_plus <- read_dist_table("./G4_seq_2015/exon.up_plus.q2.bed.score.GSE63874_Na_K_plus_hits_intersect.bed.bed.list.out.num")
G4_2015.non_template.Na_K.Q3_up_plus <- read_dist_table("./G4_seq_2015/exon.up_plus.q3.bed.score.GSE63874_Na_K_plus_hits_intersect.bed.bed.list.out.num")
G4_2015.non_template.Na_K.Q4_up_plus <- read_dist_table("./G4_seq_2015/exon.up_plus.q4.bed.score.GSE63874_Na_K_plus_hits_intersect.bed.bed.list.out.num")
G4_2015.non_template.Na_K.Q1_up_minus <- read_dist_table("./G4_seq_2015/exon.up_minus.q1.bed.score.GSE63874_Na_K_minus_hits_intersect.bed.bed.list.out.num")
G4_2015.non_template.Na_K.Q2_up_minus <- read_dist_table("./G4_seq_2015/exon.up_minus.q2.bed.score.GSE63874_Na_K_minus_hits_intersect.bed.bed.list.out.num")
G4_2015.non_template.Na_K.Q3_up_minus <- read_dist_table("./G4_seq_2015/exon.up_minus.q3.bed.score.GSE63874_Na_K_minus_hits_intersect.bed.bed.list.out.num")
G4_2015.non_template.Na_K.Q4_up_minus <- read_dist_table("./G4_seq_2015/exon.up_minus.q4.bed.score.GSE63874_Na_K_minus_hits_intersect.bed.bed.list.out.num")
G4_2015.template.Na_K.Q1_down_plus <- read_dist_table("./G4_seq_2015/exon.down_plus.q1.bed.score.GSE63874_Na_K_minus_hits_intersect.bed.bed.list.out.num")
G4_2015.template.Na_K.Q2_down_plus <- read_dist_table("./G4_seq_2015/exon.down_plus.q2.bed.score.GSE63874_Na_K_minus_hits_intersect.bed.bed.list.out.num")
G4_2015.template.Na_K.Q3_down_plus <- read_dist_table("./G4_seq_2015/exon.down_plus.q3.bed.score.GSE63874_Na_K_minus_hits_intersect.bed.bed.list.out.num")
G4_2015.template.Na_K.Q4_down_plus <- read_dist_table("./G4_seq_2015/exon.down_plus.q4.bed.score.GSE63874_Na_K_minus_hits_intersect.bed.bed.list.out.num")
G4_2015.template.Na_K.Q1_down_minus <- read_dist_table("./G4_seq_2015/exon.down_minus.q1.bed.score.GSE63874_Na_K_plus_hits_intersect.bed.bed.list.out.num")
G4_2015.template.Na_K.Q2_down_minus <- read_dist_table("./G4_seq_2015/exon.down_minus.q2.bed.score.GSE63874_Na_K_plus_hits_intersect.bed.bed.list.out.num")
G4_2015.template.Na_K.Q3_down_minus <- read_dist_table("./G4_seq_2015/exon.down_minus.q3.bed.score.GSE63874_Na_K_plus_hits_intersect.bed.bed.list.out.num")
G4_2015.template.Na_K.Q4_down_minus <- read_dist_table("./G4_seq_2015/exon.down_minus.q4.bed.score.GSE63874_Na_K_plus_hits_intersect.bed.bed.list.out.num")
G4_2015.non_template.Na_K.Q1_down_plus <- read_dist_table("./G4_seq_2015/exon.down_plus.q1.bed.score.GSE63874_Na_K_plus_hits_intersect.bed.bed.list.out.num")
G4_2015.non_template.Na_K.Q2_down_plus <- read_dist_table("./G4_seq_2015/exon.down_plus.q2.bed.score.GSE63874_Na_K_plus_hits_intersect.bed.bed.list.out.num")
G4_2015.non_template.Na_K.Q3_down_plus <- read_dist_table("./G4_seq_2015/exon.down_plus.q3.bed.score.GSE63874_Na_K_plus_hits_intersect.bed.bed.list.out.num")
G4_2015.non_template.Na_K.Q4_down_plus <- read_dist_table("./G4_seq_2015/exon.down_plus.q4.bed.score.GSE63874_Na_K_plus_hits_intersect.bed.bed.list.out.num")
G4_2015.non_template.Na_K.Q1_down_minus <- read_dist_table("./G4_seq_2015/exon.down_minus.q1.bed.score.GSE63874_Na_K_minus_hits_intersect.bed.bed.list.out.num")
G4_2015.non_template.Na_K.Q2_down_minus <- read_dist_table("./G4_seq_2015/exon.down_minus.q2.bed.score.GSE63874_Na_K_minus_hits_intersect.bed.bed.list.out.num")
G4_2015.non_template.Na_K.Q3_down_minus <- read_dist_table("./G4_seq_2015/exon.down_minus.q3.bed.score.GSE63874_Na_K_minus_hits_intersect.bed.bed.list.out.num")
G4_2015.non_template.Na_K.Q4_down_minus <- read_dist_table("./G4_seq_2015/exon.down_minus.q4.bed.score.GSE63874_Na_K_minus_hits_intersect.bed.bed.list.out.num")

G4_2015.template.Na_K.Qs.plus.up.list <- list(G4_2015.template.Na_K.Q1_up_plus, G4_2015.template.Na_K.Q2_up_plus, G4_2015.template.Na_K.Q3_up_plus, G4_2015.template.Na_K.Q4_up_plus)
G4_2015.template.Na_K.Qs.minus.list <- list(G4_2015.template.Na_K.Q1_up_minus, G4_2015.template.Na_K.Q2_up_minus, G4_2015.template.Na_K.Q3_up_minus, G4_2015.template.Na_K.Q4_up_minus)
G4_2015.template.Na_K.Qs.plus.down.list <- list(G4_2015.template.Na_K.Q1_down_plus, G4_2015.template.Na_K.Q2_down_plus, G4_2015.template.Na_K.Q3_down_plus, G4_2015.template.Na_K.Q4_down_plus)
G4_2015.template.Na_K.Qs.minus.down.list <- list(G4_2015.template.Na_K.Q1_down_minus, G4_2015.template.Na_K.Q2_down_minus, G4_2015.template.Na_K.Q3_down_minus, G4_2015.template.Na_K.Q4_down_minus)
G4_2015.template.Na_K.window_len = 2000
G4_2015.template.Na_K.Qs.total <- get_total_Qs(G4_2015.template.Na_K.Qs.plus.up.list, G4_2015.template.Na_K.Qs.minus.list, G4_2015.template.Na_K.Qs.plus.down.list, G4_2015.template.Na_K.Qs.minus.down.list, G4_2015.template.Na_K.window_len)

G4_2015.non_template.Na_K.Qs.plus.up.list <- list(G4_2015.non_template.Na_K.Q1_up_plus, G4_2015.non_template.Na_K.Q2_up_plus, G4_2015.non_template.Na_K.Q3_up_plus, G4_2015.non_template.Na_K.Q4_up_plus)
G4_2015.non_template.Na_K.Qs.minus.list <- list(G4_2015.non_template.Na_K.Q1_up_minus, G4_2015.non_template.Na_K.Q2_up_minus, G4_2015.non_template.Na_K.Q3_up_minus, G4_2015.non_template.Na_K.Q4_up_minus)
G4_2015.non_template.Na_K.Qs.plus.down.list <- list(G4_2015.non_template.Na_K.Q1_down_plus, G4_2015.non_template.Na_K.Q2_down_plus, G4_2015.non_template.Na_K.Q3_down_plus, G4_2015.non_template.Na_K.Q4_down_plus)
G4_2015.non_template.Na_K.Qs.minus.down.list <- list(G4_2015.non_template.Na_K.Q1_down_minus, G4_2015.non_template.Na_K.Q2_down_minus, G4_2015.non_template.Na_K.Q3_down_minus, G4_2015.non_template.Na_K.Q4_down_minus)
G4_2015.non_template.Na_K.window_len = 2000
G4_2015.non_template.Na_K.Qs.total <- get_total_Qs(G4_2015.non_template.Na_K.Qs.plus.up.list, G4_2015.non_template.Na_K.Qs.minus.list, G4_2015.non_template.Na_K.Qs.plus.down.list, G4_2015.non_template.Na_K.Qs.minus.down.list, G4_2015.non_template.Na_K.window_len)

G4_2015.template.Na_K.Qs.total

       Position Q Occurrences.x median.x Enrrichment.x Occurrences.y median.y Enrrichment.y Occurrences median Enrrichment   exon_pos
    1:    -1000 1          2362   2490.0     0.9485944          2292   2412.0     0.9502488        4654   4893   0.9511547   Upstream
    2:    -1000 2          1928   1952.0     0.9877049          1753   1901.0     0.9221462        3681   3861   0.9533800   Upstream
    3:    -1000 3          1549   1514.0     1.0231176          1497   1471.0     1.0176751        3046   2984   1.0207775   Upstream
    4:    -1000 4          1099   1038.0     1.0587669          1074   1000.0     1.0740000        2173   2036   1.0672888   Upstream
    5:     -999 1          2356   2490.0     0.9461847          2299   2412.0     0.9531509        4655   4893   0.9513591   Upstream
   ---                                                                                                                               
15988:      997 4          1294   1470.5     0.8799728          1309   1463.5     0.8944312        2603   2934   0.8871847 Downstream
15989:      998 1          1609   1914.0     0.8406479          1565   1797.0     0.8708959        3174   3710   0.8555256 Downstream
15990:      998 2          1556   1874.0     0.8303095          1486   1786.0     0.8320269        3042   3657   0.8318294 Downstream
15991:      998 3          1403   1633.0     0.8591549          1386   1618.0     0.8566131        2789   3265   0.8542113 Downstream
15992:      998 4          1294   1470.5     0.8799728          1305   1463.5     0.8916980        2599   2934   0.8858214 Downstream

G4_2015.non_template.Na_K.Qs.total

       Position Q Occurrences.x median.x Enrrichment.x Occurrences.y median.y Enrrichment.y Occurrences median Enrrichment   exon_pos
    1:    -1000 1          1927   2021.0     0.9534884          1792   1970.5     0.9094139        3719   3995   0.9309136   Upstream
    2:    -1000 2          1575   1674.5     0.9405793          1500   1575.5     0.9520787        3075   3242   0.9484886   Upstream
    3:    -1000 3          1265   1280.0     0.9882812          1183   1197.0     0.9883041        2448   2474   0.9894907   Upstream
    4:    -1000 4           930    926.0     1.0043197           870    852.0     1.0211268        1800   1765   1.0198300   Upstream
    5:     -999 1          1924   2021.0     0.9520040          1795   1970.5     0.9109363        3719   3995   0.9309136   Upstream
   ---                                                                                                                               
15988:      997 4          1320   1303.0     1.0130468          1142   1275.0     0.8956863        2462   2566   0.9594700 Downstream
15989:      998 1          1569   1623.0     0.9667283          1369   1523.5     0.8985888        2938   3121   0.9413649 Downstream
15990:      998 2          1468   1579.0     0.9297023          1422   1466.0     0.9699864        2890   3039   0.9509707 Downstream
15991:      998 3          1368   1408.0     0.9715909          1280   1327.0     0.9645818        2648   2734   0.9685443 Downstream
15992:      998 4          1319   1303.0     1.0122794          1145   1275.0     0.8980392        2464   2566   0.9602494 Downstream

G4_2015.template_non_template.Na_K.Qs.total <- rbind(G4_2015.template.Na_K.Qs.total, G4_2015.non_template.Na_K.Qs.total)
  
half_n <- nrow(G4_2015.template_non_template.Na_K.Qs.total)/2
G4_2015.template_non_template.Na_K.Qs.total[, Strand:=rep(c("Template", "Non-template"), each=half_n) ]
  
  
  
  
G4_2015.template_non_template.Na_K.Qs.total$Strand <-  factor(G4_2015.template_non_template.Na_K.Qs.total$Strand, levels=c("Template", "Non-template" ))
  

G4_2015.template_non_template.Na_K.Qs.total$Q <- mapvalues(G4_2015.template_non_template.Na_K.Qs.total$Q,  from =c(1:4), to =c("Q1", "Q2", "Q3", "Q4"))
G4_2015.template_non_template.Na_K.Qs.total[Strand=="Non-template" , new_Strand:="Template"]
G4_2015.template_non_template.Na_K.Qs.total[Strand=="Template" , new_Strand:="Non-template"]
G4_2015.template_non_template.Na_K.Qs.total$new_Strand <-  factor(G4_2015.template_non_template.Na_K.Qs.total$new_Strand, levels=c("Template", "Non-template" ))
ggplot(G4_2015.template_non_template.Na_K.Qs.total)+
  geom_line(aes(x=Position,y=Enrrichment, colour=Q)) +
  xlim(c(-300,300)) +
  facet_grid( new_Strand ~ exon_pos ) +
  labs(colour = "Splice site stregth quartile") +
  theme_bw()  + 
  theme(legend.position = "top", legend.direction = "horizontal")

KCl RNA-seq

As K+ is known to stabilize G4, we analized (RNA-seq data)[https://www.ncbi.nlm.nih.gov/bioproject/PRJEB19451] comming from neurons after 4-hour KCl-indused depolarization.

KCL_human_upstream <- fread("../KCL/MicroExonator/Control_vs_KCL.diff.upstream_100nt.G4s"  ) 
KCL_human_upstream <- fread("../KCL/MicroExonator/Control_vs_KCL.diff.upstream_100nt.G4s"  ) #stop here
colnames(KCL_human_upstream) <- c("w.chrom", "w.start", "w.end", "w.strand", "chrom", "start", "end", "strand", "Type", "Psi_A", "Psi_B", "DeltaPsi", "Probability", "G4"  )
KCL_human_downstream<- fread("../KCL/MicroExonator/Control_vs_KCL.diff.downstream_100nt.G4s"  )
colnames(KCL_human_downstream) <-c("w.chrom", "w.start", "w.end", "w.strand", "chrom", "start", "end", "strand", "Type", "Psi_A", "Psi_B", "DeltaPsi", "Probability", "G4"  )
KCL_human <-  merge(KCL_human_upstream[, c("chrom",  "start", "end", "strand",  "Type" , "Psi_A", "Psi_B",  "DeltaPsi", "Probability", "G4") ],
                    KCL_human_downstream[, c("chrom",  "start", "end", "strand",  "Type" , "Psi_A", "Psi_B",  "DeltaPsi", "Probability", "G4") ], 
                    by=c("chrom",  "start", "end", "strand",  "Type" , "Psi_A", "Psi_B",  "DeltaPsi", "Probability") )
KCL_human[(G4.x>0 | G4.y>0 ), G4_bol:="With G-quadruplex"]
KCL_human[(G4.x==0 & G4.y==0 ), G4_bol:="Without G-quadruplex"]
KCL_human$G4_bol <- factor(KCL_human$G4_bol, levels=c("Without G-quadruplex", "With G-quadruplex") )
KCL_human[end - start > 30, exon:="exon" ]
KCL_human[end - start <= 30, exon:="microexon" ]
size.var=0.5
alpha.var=0.25
 ggplot(data=KCL_human[ Type=="CE",]) +
  geom_point( aes(x=-DeltaPsi, y=Probability), colour="grey", alpha=alpha.var, size=size.var) +
  geom_point(data=KCL_human[Type=="CE" & DeltaPsi>0.1 & Probability>0.9, ], aes(x=-DeltaPsi, y=Probability), colour="skyblue", alpha=alpha.var, size=size.var) +
   geom_point(data=KCL_human[Type=="CE" & DeltaPsi<(-0.1) & Probability>0.9, ], aes(x=-DeltaPsi, y=Probability), colour="red", alpha=alpha.var, size=size.var) +
  xlim(c(-0.8, 0.8)) +
  facet_grid( . ~ G4_bol  ) +
  xlab("DeltaPSI (Control - KCl)") +
  theme_bw()

To highlight NRXN2, SHANK1 and RBM10 we used biomaRt to find the gene name to Ensembl ID correspondence

KCL_human[ Type=="CE"& DeltaPsi>0.1 & Probability>0.9,  ]

      chrom     start       end strand Type   Psi_A   Psi_B DeltaPsi Probability G4.x G4.y               G4_bol      exon
   1:  chr1    898717    898884      +   CE 0.98048 0.87592  0.10456       0.983    0    0 Without G-quadruplex      exon
   2:  chr1    998459    998581      +   CE 0.85834 0.19319  0.66515       1.000    0    0 Without G-quadruplex      exon
   3:  chr1   1417925   1417994      +   CE 0.98218 0.79026  0.19193       1.000    0    0 Without G-quadruplex      exon
   4:  chr1   1420396   1420551      +   CE 0.98311 0.86868  0.11443       0.989    0    1    With G-quadruplex      exon
   5:  chr1   1425072   1425191      +   CE 0.38275 0.12733  0.25542       0.995    1    0    With G-quadruplex      exon
  ---                                                                                                                    
2330:  chrX 133372809 133372870      +   CE 0.62780 0.26360  0.36421       0.968    0    0 Without G-quadruplex      exon
2331:  chrX 149882951 149883001      +   CE 0.48758 0.21579  0.27179       0.976    0    0 Without G-quadruplex      exon
2332:  chrX 153224020 153224217      -   CE 0.90752 0.73220  0.17532       0.999    0    0 Without G-quadruplex      exon
2333:  chrX 153585619 153585642      -   CE 0.50841 0.26592  0.24249       0.999    0    0 Without G-quadruplex microexon
2334:  chrX 153872153 153872305      -   CE 0.91368 0.71626  0.19742       0.923    1    0    With G-quadruplex      exon

KCL_human[, Coords:=paste(chrom, paste(start, end, sep = "-"), strand, sep=":" )]
whippet.jls.exons.hg19 <-  fread("../KCL/whippet.jls.exons.tab")
KCL_human_CE <- merge(KCL_human[Type=="CE", ], whippet.jls.exons.hg19, by.x="Coords", by.y="Potential_Exon")
KCL_human_CE[ , ensembl_gene_id:=vapply(strsplit(KCL_human_CE$Gene, ".", fixed = TRUE), "[", "", 1)]
KCL_human_CE_genes <-  data.table(getBM(attributes=c('ensembl_gene_id', "wikigene_description", "hgnc_symbol"),filters = 'ensembl_gene_id', values = unique(vapply(strsplit(KCL_human_CE$Gene, ".", fixed = TRUE), "[", "", 1)) , mart = ensembl))
KCL_human_CE <-  merge(KCL_human_CE, KCL_human_CE_genes, by="ensembl_gene_id")

KCL_human_CE[ Type=="CE"& DeltaPsi>0.1 & Probability>0.9,  ]

      ensembl_gene_id                     Coords chrom     start       end strand Type   Psi_A   Psi_B DeltaPsi Probability G4.x G4.y
   1: ENSG00000001084   chr6:53380907-53381015:-  chr6  53380907  53381015      -   CE 0.97612 0.87381  0.10231       0.981    0    0
   2: ENSG00000001167   chr6:41048550-41048636:+  chr6  41048550  41048636      +   CE 0.84244 0.36849  0.47395       1.000    0    0
   3: ENSG00000001497   chrX:64740582-64740697:-  chrX  64740582  64740697      -   CE 0.75403 0.61097  0.14306       0.929    0    0
   4: ENSG00000001629   chr7:92021555-92021606:+  chr7  92021555  92021606      +   CE 0.91807 0.79402  0.12406       0.939    0    0
   5: ENSG00000002016    chr12:1023597-1023698:- chr12   1023597   1023698      -   CE 0.93161 0.70463  0.22698       0.927    0    0
  ---                                                                                                                                
2414: ENSG00000273025  chr15:72581209-72581271:- chr15  72581209  72581271      -   CE 0.67657 0.48694  0.18962       0.912    1    1
2415: ENSG00000273025  chr15:72608186-72608268:- chr15  72608186  72608268      -   CE 0.98004 0.83100  0.14904       0.996    0    0
2416: ENSG00000273167  chr13:24591806-24591840:+ chr13  24591806  24591840      +   CE 0.86386 0.30902  0.55484       0.988    0    0
2417: ENSG00000273189  chr19:49983809-49983877:+ chr19  49983809  49983877      +   CE 0.88601 0.37471  0.51131       0.993    2    2
2418: ENSG00000273247 chr4:140373511-140373651:-  chr4 140373511 140373651      -   CE 0.79885 0.61443  0.18442       0.917    0    0
                    G4_bol exon               Gene Whippet_Nodes Is_Annotated                         wikigene_description hgnc_symbol
   1: Without G-quadruplex exon  ENSG00000001084.6            14            Y  glutamate-cysteine ligase catalytic subunit        GCLC
   2: Without G-quadruplex exon ENSG00000001167.10             4            Y nuclear transcription factor Y subunit alpha        NFYA
   3: Without G-quadruplex exon ENSG00000001497.12            16            Y         LAS1 like ribosome biogenesis factor       LAS1L
   4: Without G-quadruplex exon  ENSG00000001629.5            27            Y   ankyrin repeat and IBR domain containing 1      ANKIB1
   5: Without G-quadruplex exon ENSG00000002016.12            43            Y            RAD52 homolog, DNA repair protein       RAD52
  ---                                                                                                                                 
2414:    With G-quadruplex exon  ENSG00000273025.1             9            Y                                                         
2415: Without G-quadruplex exon  ENSG00000273025.1             2            Y                                                         
2416: Without G-quadruplex exon  ENSG00000273167.1             3            Y                                                         
2417:    With G-quadruplex exon  ENSG00000273189.1             7            Y                                                         
2418: Without G-quadruplex exon  ENSG00000273247.1             5            Y                                                         

Microexons

ME_TOTAL_chi_squared(KCL_human.TOTAL_and_ME_stats)

    Pearson's Chi-squared test with Yates' continuity correction

data:  KCL_human.TOTAL_and_ME_stats.matrix
X-squared = 178.44, df = 1, p-value < 2.2e-16

ME_TOTAL_chi_squared(KCL_human.TOTAL_and_ME_stats)

    Pearson's Chi-squared test with Yates' continuity correction

data:  KCL_human.TOTAL_and_ME_stats.matrix
X-squared = 178.44, df = 1, p-value < 2.2e-16

ME_TOTAL_chi_squared(KCL_DIV10_Tc1.TOTAL_and_ME_stats)

    Pearson's Chi-squared test with Yates' continuity correction

data:  KCL_human.TOTAL_and_ME_stats.matrix
X-squared = 130.71, df = 1, p-value < 2.2e-16

ME_TOTAL_chi_squared(KCL_ESC_CD1.TOTAL_and_ME_stats)

    Pearson's Chi-squared test with Yates' continuity correction

data:  KCL_human.TOTAL_and_ME_stats.matrix
X-squared = 326.73, df = 1, p-value < 2.2e-16

ME_TOTAL_chi_squared(KCL_DIV4_CD1.TOTAL_and_ME_stats)

    Pearson's Chi-squared test with Yates' continuity correction

data:  KCL_human.TOTAL_and_ME_stats.matrix
X-squared = 342.28, df = 1, p-value < 2.2e-16

ME_TOTAL_chi_squared(KCL_DIV10_CD1.TOTAL_and_ME_stats)

    Pearson's Chi-squared test with Yates' continuity correction

data:  KCL_human.TOTAL_and_ME_stats.matrix
X-squared = 264.99, df = 1, p-value < 2.2e-16

table(KCL_human.TOTAL_and_ME[  exon_type=="Exon", diff])

    Ex     In     NA 
  2195    276 109122 

install.packages("epiR")

Installing package into ‘/Users/gp7/Library/R/3.5/library’
(as ‘lib’ is unspecified)
also installing the dependency ‘BiasedUrn’

Warning in install.packages :
  cannot open URL 'https://cran.rstudio.com/bin/macosx/el-capitan/contrib/3.5/PACKAGES.rds': HTTP status was '404 Not Found'

trying URL 'https://cran.rstudio.com/bin/macosx/el-capitan/contrib/3.5/BiasedUrn_1.07.tgz'
Content type 'application/x-gzip' length 421842 bytes (411 KB)
==================================================
downloaded 411 KB

trying URL 'https://cran.rstudio.com/bin/macosx/el-capitan/contrib/3.5/epiR_1.0-4.tgz'
Content type 'application/x-gzip' length 574632 bytes (561 KB)
==================================================
downloaded 561 KB

The downloaded binary packages are in
    /var/folders/0h/z3ycz6gx4rj5_frl6r5wnvbw000g0g/T//RtmpkBU5sY/downloaded_packages

library("ggrepel")

package ‘ggrepel’ was built under R version 3.5.2

validation_exons <-c("chr1:110734594-110734835:+", "chr19:17731502-17731531:-", "chr11:20072835-20072879:+")
Fig5.A <- ggplot(data=KCL_human[ Type=="CE",]) +
  geom_point( aes(x=-DeltaPsi, y=Probability), colour="grey", alpha=alpha.var, size=size.var) +
  geom_point(data=KCL_human[Type=="CE" & DeltaPsi>0.1 & Probability>0.9, ], aes(x=-DeltaPsi, y=Probability), colour="skyblue", alpha=alpha.var, size=size.var) +
   geom_point(data=KCL_human[Type=="CE" & DeltaPsi<(-0.1) & Probability>0.9, ], aes(x=-DeltaPsi, y=Probability), colour="red", alpha=alpha.var, size=size.var) +
  xlim(c(-0.8, 0.8)) +
  facet_grid( . ~ G4_bol  ) +
  xlab("DeltaPSI (Control - KCl)") +
  theme_bw() +
  geom_point(data=KCL_human_CE[Coords %in% validation_exons , ], aes(x=-DeltaPsi, y=Probability), colour="blue", alpha=alpha.var, size=2) +
  geom_text_repel(data = KCL_human_CE[Coords %in% validation_exons , ],
                  colour="black", aes(x=-DeltaPsi, y=Probability),
                  nudge_y      = 3,
                  direction    = "x",
                  angle        = 90,
                  vjust        = 1,
                  segment.size = 0.2,
                  label.size = 0.05,
                  label=KCL_human_CE[Coords %in% validation_exons , hgnc_symbol]) +
  ylim(c(0.5, 1.15))

Ignoring unknown parameters: label.size

Fig5.A

To analyse all the Whippet node types, we calculate the odd-ratios of being differentially included given the G4 presence or absence

KCL_human[  , diff:="NA"]
KCL_human[ (DeltaPsi<=-0.1 & Probability>=0.9) , diff:="In"]
KCL_human[ (DeltaPsi>0.1 & Probability>=0.9) , diff:="Ex"]
KCL_human_stats <- merge(KCL_human[  G4_bol=="Without G-quadruplex",  .(WO_G4=.N) , by=c("Type", "diff")  ], 
KCL_human[  G4_bol=="With G-quadruplex",  .(W_G4=.N) , by=c("Type", "diff")  ],
by=c("Type", "diff"))

Error in .checkTypos(e, names(x)) : 
  Object 'G4_bol' not found amongst Gene, Node, Coord, Strand, Type and 7 more

We use chi-squared test to calculate the significance

KCL_human_stats.chi <- data.table()
for ( i in unique(KCL_human_stats[Type!="AL"]$Type)){
  
matrix.ex <-  matrix(nrow=2, c(KCL_human_stats[Type==i & diff=="Ex"]$WO_G4_NA, KCL_human_stats[Type==i & diff=="Ex"]$WO_G4, KCL_human_stats[Type==i & diff=="Ex"]$W_G4_NA, KCL_human_stats[Type==i & diff=="Ex"]$W_G4))
matrix.ex_res <- chisq.test(matrix.ex)
matrix.in <-  matrix(nrow=2, c(KCL_human_stats[Type==i & diff=="In"]$WO_G4_NA, KCL_human_stats[Type==i & diff=="In"]$WO_G4, KCL_human_stats[Type==i & diff=="In"]$W_G4_NA, KCL_human_stats[Type==i & diff=="In"]$W_G4))
matrix.in_res <- chisq.test(matrix.in)
KCL_human_stats.chi <- rbind(KCL_human_stats.chi, cbind(i, "Ex", matrix.ex_res$p.value)) 
KCL_human_stats.chi <- rbind(KCL_human_stats.chi, cbind(i, "In", matrix.in_res$p.value)) 
                                                        
}
colnames(KCL_human_stats.chi) <- c("Type", "diff", "P_value")
ntest = nrow(KCL_human_stats.chi)
KCL_human_stats.chi[ , `:=`(P_value.Bonferroni=as.numeric(P_value)*ntest) ]
KCL_human_stats <- merge(KCL_human_stats, KCL_human_stats.chi, by=c("Type", "diff"))

library(plyr)
ggplot(KCL_human_stats) +
  geom_point(aes(Type, diff, size = -log(P_value.Bonferroni), shape=P_value.Bonferroni<0.05, colour=log2(OR) ) ) +
  scale_colour_gradient2(low="blue", high="red", mid = "grey", midpoint = 0) +
  theme_bw() +
      theme(legend.position = "top", legend.direction = "horizontal") 

splice_node_dot_plot <- function(upstream.path, downstream.path ) {
KCL_x_upstream <- fread(upstream.path  )
colnames(KCL_x_upstream) <- c("w.chrom", "w.start", "w.end", "w.strand", "chrom", "start", "end", "strand", "Type", "Psi_A", "Psi_B", "DeltaPsi", "Probability", "G4"  )
KCL_x_downstream<- fread(downstream.path  )
colnames(KCL_x_downstream) <-c("w.chrom", "w.start", "w.end", "w.strand", "chrom", "start", "end", "strand", "Type", "Psi_A", "Psi_B", "DeltaPsi", "Probability", "G4"  )
KCL_x <-  merge(KCL_x_upstream[, c("chrom",  "start", "end", "strand",  "Type" ,  "DeltaPsi", "Probability", "G4") ],
                    KCL_x_downstream[, c("chrom",  "start", "end", "strand",  "Type" ,  "DeltaPsi", "Probability", "G4") ], 
                    by=c("chrom",  "start", "end", "strand",  "Type" ,  "DeltaPsi", "Probability") )
#KCL_x <-  KCL_x[end-start>30 || Type!="CE", ]
KCL_x[(G4.x>0 | G4.y>0 ), G4_bol:="With G-quadruplex"]
KCL_x[(G4.x==0 & G4.y==0 ), G4_bol:="Without G-quadruplex"]
KCL_x$G4_bol <- factor(KCL_x$G4_bol, levels=c("Without G-quadruplex", "With G-quadruplex") )
KCL_x[  , diff:="NA"]
KCL_x[ (DeltaPsi<=-0.1 & Probability>=0.90) , diff:="In"]
KCL_x[ (DeltaPsi>0.1 & Probability>=0.90) , diff:="Ex"]
KCL_x_stats <- merge(KCL_x[  G4_bol=="Without G-quadruplex",  .(WO_G4=.N) , by=c("Type", "diff")  ], 
KCL_x[  G4_bol=="With G-quadruplex",  .(W_G4=.N) , by=c("Type", "diff")  ],
by=c("Type", "diff"))
KCL_x_stats <- merge(KCL_x_stats[diff!="NA"],  KCL_x_stats[diff=="NA" , .(Type,  WO_G4_NA=WO_G4, W_G4_NA=W_G4) ], by="Type")
KCL_x_stats[, `:=`(WO_G4_fraq=WO_G4/WO_G4_NA, W_G4_fraq=W_G4/W_G4_NA)]
KCL_x_stats[ , OR := W_G4_fraq/WO_G4_fraq]
KCL_x_stats.chi <- data.table()
for ( i in unique(KCL_x_stats[Type!="AL"]$Type)){
  
matrix.ex <-  matrix(nrow=2, c(KCL_x_stats[Type==i & diff=="Ex"]$WO_G4_NA, KCL_x_stats[Type==i & diff=="Ex"]$WO_G4, KCL_x_stats[Type==i & diff=="Ex"]$W_G4_NA, KCL_x_stats[Type==i & diff=="Ex"]$W_G4))
matrix.ex_res <- chisq.test(matrix.ex)
matrix.in <-  matrix(nrow=2, c(KCL_x_stats[Type==i & diff=="In"]$WO_G4_NA, KCL_x_stats[Type==i & diff=="In"]$WO_G4, KCL_x_stats[Type==i & diff=="In"]$W_G4_NA, KCL_x_stats[Type==i & diff=="In"]$W_G4))
matrix.in_res <- chisq.test(matrix.in)
KCL_x_stats.chi <- rbind(KCL_x_stats.chi, cbind(i, "Ex", matrix.ex_res$p.value)) 
KCL_x_stats.chi <- rbind(KCL_x_stats.chi, cbind(i, "In", matrix.in_res$p.value)) 
                                                        
}
colnames(KCL_x_stats.chi) <- c("Type", "diff", "P_value")
ntest = nrow(KCL_x_stats.chi)
KCL_x_stats.chi[ , `:=`(P_value.Bonferroni=as.numeric(P_value)*ntest) ]
KCL_x_stats <- merge(KCL_x_stats, KCL_x_stats.chi, by=c("Type", "diff"))
ggplot(KCL_x_stats) +
  geom_point(aes(Type, diff, size = -log(P_value.Bonferroni), shape=P_value.Bonferroni<0.05, colour=log2(OR) ) ) +
  scale_colour_gradient2(low="blue", high="red", mid = "grey", midpoint = 0) +
  theme_bw() +
      theme(legend.position = "top", legend.direction = "horizontal") 
return(KCL_x_stats)
}

upstream.path = "../KCL/MicroExonator/ESC-derived_neuron_CD1.diff.upstream_100nt.G4s" 
downstream.path = "../KCL/MicroExonator/ESC-derived_neuron_CD1.diff.downstream_100nt.G4s" 
splice_node_dot_plot2 <- function(upstream.path, downstream.path ) {
KCL_x_upstream <- fread(upstream.path  )
colnames(KCL_x_upstream) <- c("w.chrom", "w.start", "w.end", "w.strand", "chrom", "start", "end", "strand", "Type", "Psi_A", "Psi_B", "DeltaPsi", "Probability", "G4"  )
KCL_x_downstream<- fread(downstream.path  )
colnames(KCL_x_downstream) <-c("w.chrom", "w.start", "w.end", "w.strand", "chrom", "start", "end", "strand", "Type", "Psi_A", "Psi_B", "DeltaPsi", "Probability", "G4"  )
KCL_x <-  merge(KCL_x_upstream[, c("chrom",  "start", "end", "strand",  "Type" ,  "DeltaPsi", "Probability", "G4") ],
                    KCL_x_downstream[, c("chrom",  "start", "end", "strand",  "Type" ,  "DeltaPsi", "Probability", "G4") ], 
                    by=c("chrom",  "start", "end", "strand",  "Type" ,  "DeltaPsi", "Probability") )
#KCL_x <-  KCL_x[end-start>30 || Type!="CE", ]
KCL_x[(G4.x>0 | G4.y>0 ), G4_bol:="With G-quadruplex"]
KCL_x[(G4.x==0 & G4.y==0 ), G4_bol:="Without G-quadruplex"]
KCL_x$G4_bol <- factor(KCL_x$G4_bol, levels=c("Without G-quadruplex", "With G-quadruplex") )
KCL_x[  , diff:="NA"]
KCL_x[ (DeltaPsi<=-0.1 & Probability>=0.90) , diff:="In"]
KCL_x[ (DeltaPsi>0.1 & Probability>=0.90) , diff:="Ex"]
KCL_x_stats <- merge(KCL_x[  G4_bol=="Without G-quadruplex",  .(WO_G4=.N) , by=c("Type", "diff")  ], 
KCL_x[  G4_bol=="With G-quadruplex",  .(W_G4=.N) , by=c("Type", "diff")  ],
by=c("Type", "diff"))
KCL_x_stats <- merge(KCL_x_stats[diff!="NA"],  KCL_x_stats[diff=="NA" , .(Type,  WO_G4_NA=WO_G4, W_G4_NA=W_G4) ], by="Type")
KCL_x_stats[, `:=`(WO_G4_fraq=WO_G4/WO_G4_NA, W_G4_fraq=W_G4/W_G4_NA)]
KCL_x_stats[ , OR := W_G4_fraq/WO_G4_fraq]
KCL_x_stats.chi <- data.table()
for ( i in unique(KCL_x_stats[Type!="AL"]$Type)){
  
matrix <-  matrix(nrow=2, c(KCL_x_stats[Type==i & diff=="In"]$WO_G4, KCL_x_stats[Type==i & diff=="Ex"]$WO_G4, KCL_x_stats[Type==i & diff=="In"]$W_G4, KCL_x_stats[Type==i & diff=="Ex"]$W_G4))
matrix.res <- chisq.test(matrix)
KCL_x_stats.chi <- rbind(KCL_x_stats.chi, cbind(i,  matrix.res$p.value)) 
                                                        
}
colnames(KCL_x_stats.chi) <- c("Type", "P_value")
ntest = nrow(KCL_x_stats.chi)
KCL_x_stats.chi[ , `:=`(P_value.Bonferroni=as.numeric(P_value)*ntest) ]
#KCL_x_stats <- merge(KCL_x_stats, KCL_x_stats.chi, by=c("Type", "diff"))
#ggplot(KCL_x_stats.chi) +
#  geom_point(aes(Type, diff, size = -log(P_value.Bonferroni), shape=P_value.Bonferroni<0.05, colour=log2(OR) ) ) +
#  scale_colour_gradient2(low="blue", high="red", mid = "grey", midpoint = 0) +
#  theme_bw() +
#      theme(legend.position = "top", legend.direction = "horizontal") 
return(KCL_x_stats.chi)
}

diff_G4_ME_table <- function(upstream.path, downstream.path, dist_lim ) {
KCL_x_upstream <- fread(upstream.path  )
colnames(KCL_x_upstream) <- c("w.chrom", "w.start", "w.end", "w.strand", "chrom", "start", "end", "strand", "Type", "Psi_A", "Psi_B", "DeltaPsi", "Probability", "gchrom", "gstart", "gend", "gscore", "exon_dist"  )
KCL_x_upstream[ ,dist:=((gstart + (gend- gstart)/2) -w.start  ) ]
#KCL_x[(dist.x<=dist_lim | dist.y<=dist_lim ), G4_bol:="With G-quadruplex"]
KCL_x_downstream<- fread(downstream.path  )
colnames(KCL_x_downstream) <- c("w.chrom", "w.start", "w.end", "w.strand", "chrom", "start", "end", "strand", "Type", "Psi_A", "Psi_B", "DeltaPsi", "Probability", "gchrom", "gstart", "gend", "gscore", "exon_dist"  )
KCL_x_downstream[ ,dist:=((gstart + (gend- gstart)/2)) - w.start   ]
KCL_x <-  merge(KCL_x_upstream[, c("chrom",  "start", "end", "strand",  "Type" ,  "DeltaPsi", "Probability", "dist") ],
                    KCL_x_downstream[, c("chrom",  "start", "end", "strand",  "Type" ,  "DeltaPsi", "Probability", "dist") ], 
                    by=c("chrom",  "start", "end", "strand",  "Type" ,  "DeltaPsi", "Probability") )
#KCL_x <-  KCL_x[end-start>30 || Type!="CE", ]
KCL_x[ , G4_bol:="Without G-quadruplex"]
KCL_x[strand=="+" & ((dist.x >= -dist_lim &  dist.x  <= 0) | ( dist.y >=0 & dist.y<=dist_lim)) , G4_bol:="With G-quadruplex"]
KCL_x[strand=="-" & ((dist.y >= -dist_lim &  dist.y  <= 0) | ( dist.x >=0 & dist.x<=dist_lim)) , G4_bol:="With G-quadruplex"]
KCL_x$G4_bol <- factor(KCL_x$G4_bol, levels=c("Without G-quadruplex", "With G-quadruplex") )
KCL_x[  , diff:="NA"]
KCL_x[ (DeltaPsi<=-0.1 & Probability>=0.90) , diff:="In"]
KCL_x[ (DeltaPsi>0.1 & Probability>=0.90) , diff:="Ex"]
KCL_x <- KCL_x[Type=="CE"]
KCL_x[ ,  exon_class:="exon"]
KCL_x[end-start<=30,  exon_class:="microexon" ]
return(KCL_x)
}

upstream.path = "../Exons_G4s/human.exons.tvs.upstream.G4seq_K"
downstream.path = "../Exons_G4s/human.exons.tvs.downstream.G4seq_K"
G4_ME_table <- function(upstream.path, downstream.path, dist_lim ) {
KCL_x_upstream <- fread(upstream.path  )
colnames(KCL_x_upstream) <- c( "chrom", "sstart", "send", "sstrand", "start", "end", "strand",  "gchrom", "gstart", "gend", "gscore", "exon_dist"  )
KCL_x_upstream[ ,dist:=(sstart - (gstart + (gend- gstart)/2)) ]
#KCL_x[(dist.x<=dist_lim | dist.y<=dist_lim ), G4_bol:="With G-quadruplex"]
KCL_x_downstream<- fread(downstream.path  )
colnames(KCL_x_downstream) <- c( "chrom", "sstart", "send", "strand", "start", "end", "strand", "gchrom", "gstart", "gend", "gscore", "exon_dist"  )
KCL_x_downstream[ ,dist:=(sstart - (gstart + (gend- gstart)/2)) ]
KCL_x <-  merge(KCL_x_upstream[, c( "chrom", "start", "end", "strand", "dist") ],
                    KCL_x_downstream[, c( "chrom", "start", "end", "strand", "dist") ], 
                    by=c( "chrom", "start", "end", "strand") )
#KCL_x <-  KCL_x[end-start>30 || Type!="CE", ]
KCL_x[ , G4_bol:="Without G-quadruplex"]
KCL_x[ strand=="+" & ((dist.x >= -dist_lim &  dist.x  <= 0) | ( dist.y >=0 & dist.y<=dist_lim)) , G4_bol:="With G-quadruplex"]
KCL_x[ strand=="-" & ((dist.y >= -dist_lim &  dist.y  <= 0) | ( dist.x >=0 & dist.x<=dist_lim)) , G4_bol:="With G-quadruplex"]
KCL_x$G4_bol <- factor(KCL_x$G4_bol, levels=c("Without G-quadruplex", "With G-quadruplex") )
KCL_x[ ,  exon_class:="exon"]
KCL_x[end-start<=30,  exon_class:="microexon" ]
return(KCL_x)
}

human.exons.upstream.G4s.300.stats <-human.exons.upstream.G4s.300[ exon_len<=150, .N  , by= c("bin", "G4_bol") ]

Error in eval(bysub, xss, parent.frame()) : object 'bin' not found

human.exons.downstream.G4s <- fread("../Exons_G4s/human.exons.tvs.downstream.G4seq_PDS")
colnames(human.exons.downstream.G4s) <- c( "chrom", "sstart", "send", "sstrand", "start", "end", "strand",  "gchrom", "gstart", "gend", "gscore", "exon_dist"  )
human.exons.downstream.G4s[ ,dist:=( (gstart + (gend- gstart)/2) - sstart) ]
human.exons.downstream.G4s[ sstrand=="-", dist:=(   sstart - (gstart + (gend- gstart)/2)) ]
human.exons.downstream.G4s[, exon_len:=end-start]
human.exons.downstream.G4s[ , G4_bol:="Without G-quadruplex"]
human.exons.downstream.G4s[ dist<=100  & dist>=0 , G4_bol:="With G-quadruplex"]
human.exons.downstream.G4s[, exon_class:="exon"]
human.exons.downstream.G4s[ exon_len<=30, exon_class:="microexon"]
human.exons.downstream.G4s.2x2 <- matrix(ncol = 2,
c(nrow(human.exons.downstream.G4s[ exon_class=="exon" & G4_bol=="Without G-quadruplex"]),
nrow(human.exons.downstream.G4s[ exon_class=="exon" & G4_bol=="With G-quadruplex"]),
nrow(human.exons.downstream.G4s[ exon_class=="microexon" & G4_bol=="Without G-quadruplex"]),
nrow(human.exons.downstream.G4s[ exon_class=="microexon" & G4_bol=="With G-quadruplex"]) ))
chisq.test(human.exons.downstream.G4s.2x2)

    Pearson's Chi-squared test with Yates' continuity correction

data:  human.exons.downstream.G4s.2x2
X-squared = 8.2286, df = 1, p-value = 0.004123

human.exons.downstream.G4s[ , ID:=paste(chrom,   start,     end, sep="_" )]
human.exons.downstream.G4s[, filter:="Out"]
human.exons.downstream.G4s[ ID %in%  KCL_human_CE,  filter:="In"]
human.exons.downstream.G4s <- human.exons.downstream.G4s[ ID %in%  KCL_human_CE, ]
human.exons.downstream.G4s.stats <-human.exons.downstream.G4s[ exon_len<=300, .N  , by= c("exon_len", "G4_bol") ]
human.exons.downstream.G4s.stats[, Total:=sum(N), by=exon_len]
human.exons.downstream.G4s.stats[, Percentage:=N*100/Total]
human.exons.downstream.G4s$G4_bol <- factor(human.exons.downstream.G4s$G4_bol, levels=c("Without G-quadruplex", "With G-quadruplex"))
ggplot(human.exons.downstream.G4s) +
  geom_bar(aes(x=exon_len, fill=G4_bol), position = "fill" ) +
  xlim(c(1, 300)) +
  geom_vline(xintercept = 30, linetype="dashed", colour="red") +
  ylim(c(0, 0.1))

ggplot(human.exons.downstream.G4s.stats[G4_bol=="With G-quadruplex"]) +
  geom_bar(aes(x=exon_len, y=Percentage), stat = "identity" ) +
  xlim(c(1, 300)) +
  geom_vline(xintercept = 30, linetype="dashed", colour="red") 

ggplot(human.exons.upstream.G4s) +
  geom_bar(aes(x=exon_len, fill=G4_bol), position = "fill" ) +
  xlim(c(1, 150)) +
  geom_vline(xintercept = 30) +
  ylim(c(0.8, 1))

ggplot(hg19_ME_table_G4s) + 
  geom_boxplot(aes(G4_bol, exon_len)) +
  ylim(c(0, 300))

hg19_ME_table_K[, exon_len:=end-start]
ggplot(hg19_ME_table_K) + 
  geom_boxplot(aes(G4_bol, exon_len)) +
  ylim(c(0, 300))

hg19_ME_table_G4s[, median(exon_len), by=G4_bol]

                 G4_bol  V1
1: Without G-quadruplex 147
2:    With G-quadruplex 174

hg19_ME_table_K[, median(exon_len), by=G4_bol]

                 G4_bol  V1
1: Without G-quadruplex 147
2:    With G-quadruplex 183

ggplot(hg19_ME_table_PDS) + 
  geom_boxplot(aes(G4_bol, exon_len)) +
  ylim(c(0, 300))

Error in FUN(X[[i]], ...) : object 'exon_len' not found

human.ME_g4.stats <- data.table()
hg19_ME_table_G4s <- G4_ME_table("../Exons_G4s/human.exons.tvs.upstream.G4s" , "../Exons_G4s/human.exons.tvs.downstream.G4s", 100 )
hg19_ME_table_G4s.2x2 <- matrix(ncol = 2,
c(nrow(hg19_ME_table_G4s[ exon_class=="exon" & G4_bol=="Without G-quadruplex"]),
nrow(hg19_ME_table_G4s[ exon_class=="exon" & G4_bol=="With G-quadruplex"]),
nrow(hg19_ME_table_G4s[ exon_class=="microexon" & G4_bol=="Without G-quadruplex"]),
nrow(hg19_ME_table_G4s[ exon_class=="microexon" & G4_bol=="With G-quadruplex"]) ))
hg19_ME_table_G4s[ , exon_len:=end-start]
colnames(hg19_ME_table_G4s.2x2) <- c("exon", "microexon")
rownames(hg19_ME_table_G4s.2x2) <- c("Without G-quadruplex", "With G-quadruplex")
human.ME_g4.stats <- rbind(human.ME_g4.stats,
                           cbind(
                             "motif",
                             chisq.test( hg19_ME_table_G4s.2x2)$p.value,
                             (hg19_ME_table_G4s.2x2[ 2 , 2 ]/hg19_ME_table_G4s.2x2[ 1 , 2 ]) / (hg19_ME_table_G4s.2x2[ 2 , 1 ]/hg19_ME_table_G4s.2x2[ 1 , 1 ])
                             ))
hg19_ME_table_K <- G4_ME_table("../Exons_G4s/human.exons.tvs.upstream.G4seq_K" , "../Exons_G4s/human.exons.tvs.downstream.G4seq_K", 100 )
hg19_ME_table_K.2x2 <- matrix(ncol = 2,
c(nrow(hg19_ME_table_K[ exon_class=="exon" & G4_bol=="Without G-quadruplex"]),
nrow(hg19_ME_table_K[ exon_class=="exon" & G4_bol=="With G-quadruplex"]),
nrow(hg19_ME_table_K[ exon_class=="microexon" & G4_bol=="Without G-quadruplex"]),
nrow(hg19_ME_table_K[ exon_class=="microexon" & G4_bol=="With G-quadruplex"]) ))
chisq.test( hg19_ME_table_K.2x2)

    Pearson's Chi-squared test with Yates' continuity correction

data:  hg19_ME_table_K.2x2
X-squared = 775.72, df = 1, p-value < 2.2e-16

human.ME_g4.stats <- rbind(human.ME_g4.stats,
                           cbind(
                             "K+",
                             chisq.test( hg19_ME_table_K.2x2)$p.value,
                             (hg19_ME_table_K.2x2[ 2 , 2 ]/hg19_ME_table_K.2x2[ 1 , 2 ]) / (hg19_ME_table_K.2x2[ 2 , 1 ]/hg19_ME_table_K.2x2[ 1 , 1 ])
                             ))
hg19_ME_table_PDS <- G4_ME_table("../Exons_G4s/human.exons.tvs.upstream.G4seq_PDS" , "../Exons_G4s/human.exons.tvs.downstream.G4seq_PDS", 100 )
hg19_ME_table_PDS.2x2 <- matrix(ncol = 2,
c(nrow(hg19_ME_table_PDS[ exon_class=="exon" & G4_bol=="Without G-quadruplex"]),
nrow(hg19_ME_table_PDS[ exon_class=="exon" & G4_bol=="With G-quadruplex"]),
nrow(hg19_ME_table_PDS[ exon_class=="microexon" & G4_bol=="Without G-quadruplex"]),
nrow(hg19_ME_table_PDS[ exon_class=="microexon" & G4_bol=="With G-quadruplex"]) ))
chisq.test( hg19_ME_table_PDS.2x2)

    Pearson's Chi-squared test with Yates' continuity correction

data:  hg19_ME_table_PDS.2x2
X-squared = 1311.3, df = 1, p-value < 2.2e-16

human.ME_g4.stats <- rbind(human.ME_g4.stats,
                           cbind(
                             "PDS",
                             chisq.test( hg19_ME_table_PDS.2x2)$p.value,
                             (hg19_ME_table_PDS.2x2[ 2 , 2 ]/hg19_ME_table_PDS.2x2[ 1 , 2 ]) / (hg19_ME_table_PDS.2x2[ 2 , 1 ]/hg19_ME_table_PDS.2x2[ 1 , 1 ])
                             ))

colnames(human.ME_g4.stats) <- c("G4_signal", "p.value", "OR") 
human.ME_g4.stats[, P_value.Bonferroni:=as.numeric(p.value)*3]
ggplot(human.ME_g4.stats) +
  geom_point(aes(G4_signal, log2(as.numeric(OR)), size = -log10(P_value.Bonferroni), shape=P_value.Bonferroni<0.05 ) ) +
  scale_colour_gradient2(low="blue", high="red", mid = "grey", midpoint = 0) +
  theme_bw() +
      theme(legend.position = "top", legend.direction = "horizontal") 

primary_cortical_neuron_DIV4_CD1_K_ME_table <- diff_G4_ME_table("../KCL/MicroExonator/closest/primary_cortical_neuron_DIV4_CD1.diff.upstream.G4seq_K" , "../KCL/MicroExonator/closest/primary_cortical_neuron_DIV4_CD1.diff.downstream.G4seq_K", 100 )
ESC_derived_neuron_CD1_K_ME_table <- diff_G4_ME_table("../KCL/MicroExonator/closest/ESC-derived_neuron_CD1.diff.upstream.G4seq_K" , "../KCL/MicroExonator/closest/ESC-derived_neuron_CD1.diff.downstream.G4seq_K", 100 )
primary_cortical_neuron_DIV10_CD1_K_ME_table <- diff_G4_ME_table("../KCL/MicroExonator/closest/primary_cortical_neuron_DIV10_CD1.diff.upstream.G4seq_K" , "../KCL/MicroExonator/closest/primary_cortical_neuron_DIV10_CD1.diff.downstream.G4seq_K", 100 )
primary_cortical_neuron_DIV10_Tc1_K_ME_table <- diff_G4_ME_table("../KCL/MicroExonator/closest/primary_cortical_neuron_DIV10_Tc1.diff.upstream.G4seq_K" , "../KCL/MicroExonator/closest/primary_cortical_neuron_DIV10_Tc1.diff.downstream.G4seq_K", 100 )
total_mouse_K_ME_table <- unique(rbind(primary_cortical_neuron_DIV4_CD1_K_ME_table[ , c("chrom" ,"start", "end", "strand", "Type", "G4_bol", "exon_class")],
ESC_derived_neuron_CD1_K_ME_table[ , c("chrom" ,"start", "end", "strand", "Type", "G4_bol", "exon_class")],
primary_cortical_neuron_DIV10_CD1_K_ME_table[ , c("chrom" ,"start", "end", "strand", "Type", "G4_bol", "exon_class")],
primary_cortical_neuron_DIV10_Tc1_K_ME_table[ , c("chrom" ,"start", "end", "strand", "Type", "G4_bol", "exon_class")]))
total_mouse_K_ME_table.2x2 <- matrix(ncol = 2,
c(nrow(total_mouse_K_ME_table[ exon_class=="exon" & G4_bol=="Without G-quadruplex"]),
nrow(total_mouse_K_ME_table[ exon_class=="exon" & G4_bol=="With G-quadruplex"]),
nrow(total_mouse_K_ME_table[ exon_class=="microexon" & G4_bol=="Without G-quadruplex"]),
nrow(total_mouse_K_ME_table[ exon_class=="microexon" & G4_bol=="With G-quadruplex"]) ))
chisq.test( total_mouse_K_ME_table.2x2)

    Pearson's Chi-squared test with Yates' continuity correction

data:  total_mouse_K_ME_table.2x2
X-squared = 1.9867, df = 1, p-value = 0.1587

colnames(total_mouse_K_ME_table.2x2) <- c("exon", "microexon")
rownames(total_mouse_K_ME_table.2x2) <- c("Without G-quadruplex", "With G-quadruplex")
primary_cortical_neuron_DIV4_CD1_PDS_ME_table <- diff_G4_ME_table("../KCL/MicroExonator/closest/primary_cortical_neuron_DIV4_CD1.diff.upstream.G4seq_PDS" , "../KCL/MicroExonator/closest/primary_cortical_neuron_DIV4_CD1.diff.downstream.G4seq_PDS", 100 )
ESC_derived_neuron_CD1_PDS_ME_table <- diff_G4_ME_table("../KCL/MicroExonator/closest/ESC-derived_neuron_CD1.diff.upstream.G4seq_PDS" , "../KCL/MicroExonator/closest/ESC-derived_neuron_CD1.diff.downstream.G4seq_PDS", 100 )
primary_cortical_neuron_DIV10_CD1_PDS_ME_table <- diff_G4_ME_table("../KCL/MicroExonator/closest/primary_cortical_neuron_DIV10_CD1.diff.upstream.G4seq_PDS" , "../KCL/MicroExonator/closest/primary_cortical_neuron_DIV10_CD1.diff.downstream.G4seq_PDS", 100 )
primary_cortical_neuron_DIV10_Tc1_PDS_ME_table <- diff_G4_ME_table("../KCL/MicroExonator/closest/primary_cortical_neuron_DIV10_Tc1.diff.upstream.G4seq_PDS" , "../KCL/MicroExonator/closest/primary_cortical_neuron_DIV10_Tc1.diff.downstream.G4seq_PDS", 100 )
total_mouse_PDS_ME_table <- unique(rbind(primary_cortical_neuron_DIV4_CD1_PDS_ME_table[ , c("chrom" ,"start", "end", "strand", "Type", "G4_bol", "exon_class")],
ESC_derived_neuron_CD1_PDS_ME_table[ , c("chrom" ,"start", "end", "strand", "Type", "G4_bol", "exon_class")],
primary_cortical_neuron_DIV10_CD1_PDS_ME_table[ , c("chrom" ,"start", "end", "strand", "Type", "G4_bol", "exon_class")],
primary_cortical_neuron_DIV10_Tc1_PDS_ME_table[ , c("chrom" ,"start", "end", "strand", "Type", "G4_bol", "exon_class")]))
total_mouse_PDS_ME_table.2x2 <- matrix(ncol = 2,
c(nrow(total_mouse_PDS_ME_table[ exon_class=="exon" & G4_bol=="Without G-quadruplex"]),
nrow(total_mouse_PDS_ME_table[ exon_class=="exon" & G4_bol=="With G-quadruplex"]),
nrow(total_mouse_PDS_ME_table[ exon_class=="microexon" & G4_bol=="Without G-quadruplex"]),
nrow(total_mouse_PDS_ME_table[ exon_class=="microexon" & G4_bol=="With G-quadruplex"]) ))
chisq.test( total_mouse_PDS_ME_table.2x2)

    Pearson's Chi-squared test with Yates' continuity correction

data:  total_mouse_PDS_ME_table.2x2
X-squared = 3.915e-27, df = 1, p-value = 1

KCL_human[, ID:=paste( chrom, strand, start, end  , sep="_")]
primary_cortical_neuron_DIV4_CD1_motif_ME_table <- diff_G4_ME_table("../KCL/MicroExonator/closest/primary_cortical_neuron_DIV4_CD1.diff.upstream.G4s.fix" , "../KCL/MicroExonator/closest/primary_cortical_neuron_DIV4_CD1.diff.downstream.G4s.fix", 100 )
ESC_derived_neuron_CD1_motif_ME_table <- diff_G4_ME_table("../KCL/MicroExonator/closest/ESC-derived_neuron_CD1.diff.upstream.G4s.fix" , "../KCL/MicroExonator/closest/ESC-derived_neuron_CD1.diff.downstream.G4s.fix", 100 )
primary_cortical_neuron_DIV10_CD1_motif_ME_table <- diff_G4_ME_table("../KCL/MicroExonator/closest/primary_cortical_neuron_DIV10_CD1.diff.upstream.G4s.fix" , "../KCL/MicroExonator/closest/primary_cortical_neuron_DIV10_CD1.diff.downstream.G4s.fix", 100 )
primary_cortical_neuron_DIV10_Tc1_motif_ME_table <- diff_G4_ME_table("../KCL/MicroExonator/closest/primary_cortical_neuron_DIV10_Tc1.diff.upstream.G4s.fix" , "../KCL/MicroExonator/closest/primary_cortical_neuron_DIV10_Tc1.diff.downstream.G4s.fix", 100 )
primary_cortical_neuron_DIV4_CD1_motif_ME_table[, ID:=paste( chrom, strand, start, end  , sep="_")]
ESC_derived_neuron_CD1_motif_ME_table[, ID:=paste( chrom, strand, start, end  , sep="_")]
primary_cortical_neuron_DIV10_CD1_motif_ME_table[, ID:=paste( chrom, strand, start, end  , sep="_")]
primary_cortical_neuron_DIV10_Tc1_motif_ME_table[, ID:=paste( chrom, strand, start, end  , sep="_")]
primary_cortical_neuron_DIV4_CD1_K_ME_table[, ID:=paste( chrom, strand, start, end  , sep="_")]
ESC_derived_neuron_CD1_K_ME_table[, ID:=paste( chrom, strand, start, end  , sep="_")]
primary_cortical_neuron_DIV10_CD1_K_ME_table[, ID:=paste( chrom, strand, start, end  , sep="_")]
primary_cortical_neuron_DIV10_Tc1_K_ME_table[, ID:=paste( chrom, strand, start, end  , sep="_")]
primary_cortical_neuron_DIV4_CD1_PDS_ME_table[, ID:=paste( chrom, strand, start, end  , sep="_")]
ESC_derived_neuron_CD1_PDS_ME_table[, ID:=paste( chrom, strand, start, end  , sep="_")]
primary_cortical_neuron_DIV10_CD1_PDS_ME_table[, ID:=paste( chrom, strand, start, end  , sep="_")]
primary_cortical_neuron_DIV10_Tc1_PDS_ME_table[, ID:=paste( chrom, strand, start, end  , sep="_")]
All_mouse <- data.table(unique(c(primary_cortical_neuron_DIV4_CD1_K_ME_table[G4_bol=="With G-quadruplex", ID],
ESC_derived_neuron_CD1_K_ME_table[G4_bol=="With G-quadruplex", ID],
primary_cortical_neuron_DIV10_CD1_K_ME_table[G4_bol=="With G-quadruplex", ID],
primary_cortical_neuron_DIV10_Tc1_K_ME_table[G4_bol=="With G-quadruplex", ID],
primary_cortical_neuron_DIV4_CD1_PDS_ME_table[G4_bol=="With G-quadruplex", ID],
ESC_derived_neuron_CD1_PDS_ME_table[G4_bol=="With G-quadruplex", ID],
primary_cortical_neuron_DIV10_CD1_PDS_ME_table[G4_bol=="With G-quadruplex", ID],
primary_cortical_neuron_DIV10_Tc1_PDS_ME_table[G4_bol=="With G-quadruplex", ID],
primary_cortical_neuron_DIV4_CD1_motif_ME_table[G4_bol=="With G-quadruplex", ID],
ESC_derived_neuron_CD1_motif_ME_table[G4_bol=="With G-quadruplex", ID],
primary_cortical_neuron_DIV10_CD1_motif_ME_table[G4_bol=="With G-quadruplex", ID],
primary_cortical_neuron_DIV10_Tc1_motif_ME_table[G4_bol=="With G-quadruplex", ID])))
colnames(All_mouse) <- "ID"
All_mouse[ ID %in% primary_cortical_neuron_DIV4_CD1_motif_ME_table[abs(DeltaPsi)>=0.1 & Probability>=0.9 & G4_bol=="With G-quadruplex", ID ], primary_cortical_neuron_DIV4_CD1_motif:=TRUE   ]
All_mouse[ ID %in% ESC_derived_neuron_CD1_motif_ME_table[abs(DeltaPsi)>=0.1 & Probability>=0.9 & G4_bol=="With G-quadruplex", ID ], ESC_derived_neuron_CD1_motif:=TRUE   ]
All_mouse[ ID %in% primary_cortical_neuron_DIV10_CD1_motif_ME_table[abs(DeltaPsi)>=0.1 & Probability>=0.9 & G4_bol=="With G-quadruplex", ID ], primary_cortical_neuron_DIV10_CD1_motif:=TRUE   ]
All_mouse[ ID %in% primary_cortical_neuron_DIV10_Tc1_motif_ME_table[abs(DeltaPsi)>=0.1 & Probability>=0.9 & G4_bol=="With G-quadruplex", ID ], primary_cortical_neuron_DIV10_Tc1_motif:=TRUE   ]
All_mouse[ ID %in% primary_cortical_neuron_DIV4_CD1_K_ME_table[abs(DeltaPsi)>=0.1 & Probability>=0.9 & G4_bol=="With G-quadruplex", ID ], primary_cortical_neuron_DIV4_CD1_K:=TRUE   ]
All_mouse[ ID %in% ESC_derived_neuron_CD1_K_ME_table[abs(DeltaPsi)>=0.1 & Probability>=0.9 & G4_bol=="With G-quadruplex", ID ], ESC_derived_neuron_CD1_K:=TRUE   ]
All_mouse[ ID %in% primary_cortical_neuron_DIV10_CD1_K_ME_table[abs(DeltaPsi)>=0.1 & Probability>=0.9 & G4_bol=="With G-quadruplex", ID ], primary_cortical_neuron_DIV10_CD1_K:=TRUE   ]
All_mouse[ ID %in% primary_cortical_neuron_DIV10_Tc1_K_ME_table[abs(DeltaPsi)>=0.1 & Probability>=0.9 & G4_bol=="With G-quadruplex", ID ], primary_cortical_neuron_DIV10_Tc1_K:=TRUE   ]
All_mouse[ ID %in% primary_cortical_neuron_DIV4_CD1_PDS_ME_table[abs(DeltaPsi)>=0.1 & Probability>=0.9 & G4_bol=="With G-quadruplex", ID ], primary_cortical_neuron_DIV4_CD1_PDS:=TRUE   ]
All_mouse[ ID %in% ESC_derived_neuron_CD1_PDS_ME_table[abs(DeltaPsi)>=0.1 & Probability>=0.9 & G4_bol=="With G-quadruplex", ID ], ESC_derived_neuron_CD1_PDS:=TRUE   ]
All_mouse[ ID %in% primary_cortical_neuron_DIV10_CD1_PDS_ME_table[abs(DeltaPsi)>=0.1 & Probability>=0.9 & G4_bol=="With G-quadruplex", ID ], primary_cortical_neuron_DIV10_CD1_PDS:=TRUE   ]
All_mouse[ ID %in% primary_cortical_neuron_DIV10_Tc1_PDS_ME_table[abs(DeltaPsi)>=0.1 & Probability>=0.9 & G4_bol=="With G-quadruplex", ID ], primary_cortical_neuron_DIV10_Tc1_PDS:=TRUE   ]
All_mouse <- cbind(All_mouse, rowSums(is.na(All_mouse)))
fwrite(All_mouse[order(V2)], "../potassium_experiments/Total_mouse.txt", na="FALSE", sep = "\t", quote=F)
       
       
human_motif_ME_table <- diff_G4_ME_table("../KCL/MicroExonator/closest/Control_vs_KCL.diff.upstream.G4s" , "../KCL/MicroExonator/closest/Control_vs_KCL.diff.downstream.G4s", 100 )   
human_K_ME_table <- diff_G4_ME_table("../KCL/MicroExonator/closest/Control_vs_KCL.diff.upstream.G4seq_K" , "../KCL/MicroExonator/closest/Control_vs_KCL.diff.downstream.G4seq_K", 100 )
human_PDS_ME_table <- diff_G4_ME_table("../KCL/MicroExonator/closest/Control_vs_KCL.diff.upstream.G4seq_PDS" , "../KCL/MicroExonator/closest/Control_vs_KCL.diff.downstream.G4seq_PDS", 100 )   
     
human_motif_ME_table[, ID:=paste( chrom, strand, start, end  , sep="_")]
human_K_ME_table[, ID:=paste( chrom, strand, start, end  , sep="_")]
human_PDS_ME_table[, ID:=paste( chrom, strand, start, end  , sep="_")]
All_human<- data.table(unique(c(         
human_motif_ME_table[G4_bol=="With G-quadruplex", ID],       
human_K_ME_table[G4_bol=="With G-quadruplex", ID],
human_PDS_ME_table[G4_bol=="With G-quadruplex", ID])))
colnames(All_human) <- "ID"
All_human[ ID %in% human_motif_ME_table[abs(DeltaPsi)>=0.1 & Probability>=0.9 & G4_bol=="With G-quadruplex", ID ], diff_motif:=TRUE   ]
All_human[ ID %in% human_K_ME_table[abs(DeltaPsi)>=0.1 & Probability>=0.9 & G4_bol=="With G-quadruplex", ID ], diff_K:=TRUE   ]
All_human[ ID %in% human_PDS_ME_table[abs(DeltaPsi)>=0.1 & Probability>=0.9 & G4_bol=="With G-quadruplex", ID ], diff_:=TRUE   ]
All_human <- cbind(All_human, rowSums(is.na(All_human)))
fwrite(All_human[order(V2)], "../potassium_experiments/Total_human.txt",  na="FALSE", sep = "\t", quote=F)

Not working

human_mouse <- fread("../potassium_experiments/human_mouse.0.2.exons")
colnames(human_mouse) <- c("hID", "mID", "score_index")
All_human.mouse <- merge(All_human, human_mouse, by.x="ID", by.y="hID")
All_human.mouse <- merge(All_human.mouse, All_mouse, by.x = "mID", by.y="ID")
All_human.mouse.diff <-  All_human.mouse[V2.y<12 & V2.x<3 ]
All_human.mouse.diff

                            mID                          ID diff_motif diff_K diff_ V2.x score_index primary_cortical_neuron_DIV4_CD1_motif ESC_derived_neuron_CD1_motif
 1:   chr10_+_81317326_81317403     chr19_-_3633435_3633518         NA     NA  TRUE    2 0.000000000                                     NA                           NA
 2: chr10_-_127662731_127662922   chr12_+_57487190_57487381       TRUE   TRUE  TRUE    0 0.000000000                                     NA                           NA
 3:     chr11_+_6398262_6398339    chr7_+_44799750_44799827       TRUE   TRUE  TRUE    0 0.000000000                                     NA                         TRUE
 4:   chr11_+_97491644_97491666   chr17_+_36655174_36655196         NA   TRUE  TRUE    1 0.043478261                                     NA                           NA
 5: chr11_-_102310926_102311036   chr17_-_42289712_42289822       TRUE     NA    NA    2 0.000000000                                   TRUE                         TRUE
 6:     chr11_-_4485879_4485989   chr22_+_30418018_30418128       TRUE   TRUE  TRUE    0 0.000000000                                     NA                           NA
 7:   chr11_-_69830563_69830613     chr17_+_7315476_7315526         NA   TRUE  TRUE    1 0.000000000                                     NA                           NA
 8:   chr12_-_84613905_84614044   chr14_-_74764633_74764772         NA     NA  TRUE    2 0.000000000                                     NA                           NA
 9: chr13_-_111447896_111447955    chr5_+_56532940_56532999         NA   TRUE  TRUE    1 0.000000000                                     NA                           NA
10:   chr14_-_36890342_36890426   chr10_+_86259631_86259715         NA     NA  TRUE    2 0.000000000                                     NA                           NA
11: chr15_+_102519122_102519291   chr12_+_53895844_53895968         NA     NA  TRUE    2 0.008000000                                     NA                           NA
12:   chr15_+_99305166_99305193   chr12_+_50026379_50026406         NA     NA  TRUE    2 0.035714286                                     NA                           NA
13:   chr16_+_20673599_20673655  chr3_+_184033277_184033333       TRUE     NA  TRUE    1 0.000000000                                     NA                           NA
14:   chr16_+_20695739_20695881  chr3_+_184056175_184056317         NA   TRUE  TRUE    1 0.027972028                                     NA                           NA
15:     chr16_+_3745777_3745957     chr16_+_3335059_3335239       TRUE     NA    NA    2 0.000000000                                     NA                           NA
16:   chr17_+_25818498_25818582       chr16_-_744992_745076       TRUE   TRUE  TRUE    0 0.000000000                                     NA                           NA
17:   chr17_-_24182786_24182849     chr16_+_2549358_2549421         NA     NA  TRUE    2 0.140625000                                     NA                         TRUE
18:   chr18_+_32430750_32430857  chr2_-_127809831_127809938       TRUE     NA    NA    2 0.000000000                                     NA                           NA
19:   chr18_+_74275904_74276071   chr18_-_47800556_47800720       TRUE     NA  TRUE    1 0.006060606                                     NA                           NA
20:     chr19_+_6488784_6488810   chr11_-_64421168_64421194       TRUE   TRUE  TRUE    0 0.037037037                                   TRUE                           NA
21:     chr19_+_8830888_8830961   chr11_-_62483336_62483409         NA     NA  TRUE    2 0.000000000                                     NA                           NA
22:    chr2_+_76560186_76560260  chr2_+_179209013_179209087         NA     NA  TRUE    2 0.000000000                                     NA                           NA
23:    chr2_+_91805024_91805110   chr11_-_46534277_46534363         NA     NA  TRUE    2 0.000000000                                     NA                           NA
24:  chr2_-_152323172_152323332       chr20_+_401515_401650       TRUE   TRUE  TRUE    0 0.007352941                                     NA                           NA
25:    chr2_-_30348555_30348617  chr9_-_131774515_131774577       TRUE   TRUE  TRUE    0 0.000000000                                     NA                           NA
26:    chr3_+_88158034_88158171  chr1_-_156450626_156450763       TRUE   TRUE  TRUE    0 0.000000000                                     NA                           NA
27:    chr3_+_94989303_94989347  chr1_-_151282687_151282731       TRUE   TRUE    NA    1 0.022222222                                   TRUE                         TRUE
28:    chr3_+_95167999_95168100  chr1_-_151111106_151111207       TRUE     NA    NA    2 0.049019608                                   TRUE                         TRUE
29:  chr3_-_107477177_107477418  chr1_+_110734594_110734835       TRUE     NA  TRUE    1 0.000000000                                     NA                           NA
30:  chr3_-_148860427_148860438    chr1_+_82407718_82407729         NA     NA  TRUE    2 0.083333333                                   TRUE                           NA
31:  chr4_+_118410887_118411003    chr1_-_43853981_43854099       TRUE   TRUE  TRUE    0 0.016806723                                     NA                           NA
32:  chr4_+_152385724_152385838      chr1_-_6166455_6166569       TRUE     NA  TRUE    1 0.000000000                                     NA                           NA
33:  chr4_-_126238522_126238632    chr1_+_36640499_36640609       TRUE     NA    NA    2 0.000000000                                   TRUE                         TRUE
34:  chr4_-_129637096_129637187    chr1_+_32650126_32650217         NA     NA  TRUE    2 0.000000000                                     NA                           NA
35:  chr5_-_134504734_134504838    chr7_+_73787262_73787366       TRUE   TRUE    NA    1 0.000000000                                   TRUE                         TRUE
36:  chr5_-_137301318_137301647  chr7_+_100480386_100480711         NA     NA  TRUE    2 0.000000000                                     NA                           NA
37:  chr7_+_123124668_123124715   chr16_+_24741574_24741621         NA     NA  TRUE    2 0.020833333                                     NA                           NA
38:  chr7_+_127485928_127485996   chr16_+_30676959_30677027       TRUE     NA  TRUE    1 0.014492754                                   TRUE                           NA
39:  chr7_+_127487265_127487336   chr16_+_30678240_30678311       TRUE     NA  TRUE    1 0.138888889                                   TRUE                           NA
40:  chr7_+_139852512_139852657 chr10_+_134916201_134916346         NA     NA  TRUE    2 0.000000000                                     NA                           NA
41:    chr7_+_49554215_49554259   chr11_+_20072835_20072879       TRUE     NA    NA    2 0.022222222                                     NA                           NA
42:  chr7_-_126492449_126492485   chr16_+_28847770_28847806       TRUE     NA  TRUE    1 0.027027027                                     NA                           NA
43:  chr7_-_126857226_126857291   chr16_+_30012786_30012851         NA     NA  TRUE    2 0.000000000                                     NA                           NA
44:    chr7_-_28895121_28895180   chr19_+_39218956_39219021         NA   TRUE  TRUE    1 0.090909091                                     NA                           NA
45:    chr7_-_28895432_28895512   chr19_+_39218586_39218666         NA   TRUE  TRUE    1 0.000000000                                     NA                           NA
46:      chr8_+_3600358_3600405     chr19_+_7672707_7672754       TRUE   TRUE    NA    1 0.020833333                                     NA                           NA
47:    chr8_-_71636538_71636567   chr19_-_17731502_17731531       TRUE   TRUE  TRUE    0 0.033333333                                   TRUE                         TRUE
48:  chr9_+_108838760_108838774    chr3_-_48687708_48687722         NA   TRUE  TRUE    1 0.066666667                                     NA                           NA
49:    chr9_+_45912951_45913041 chr11_-_117096647_117096737         NA     NA  TRUE    2 0.000000000                                     NA                           NA
50:  chr9_-_119973364_119973678    chr3_-_39185628_39185942         NA     NA  TRUE    2 0.158730159                                     NA                           NA
    primary_cortical_neuron_DIV10_CD1_motif primary_cortical_neuron_DIV10_Tc1_motif primary_cortical_neuron_DIV4_CD1_K ESC_derived_neuron_CD1_K primary_cortical_neuron_DIV10_CD1_K
 1:                                      NA                                      NA                               TRUE                       NA                                  NA
 2:                                      NA                                      NA                                 NA                       NA                                  NA
 3:                                      NA                                      NA                                 NA                     TRUE                                  NA
 4:                                      NA                                      NA                                 NA                       NA                                  NA
 5:                                    TRUE                                      NA                               TRUE                     TRUE                                TRUE
 6:                                      NA                                      NA                                 NA                       NA                                  NA
 7:                                      NA                                      NA                                 NA                       NA                                  NA
 8:                                      NA                                      NA                                 NA                       NA                                  NA
 9:                                      NA                                      NA                               TRUE                     TRUE                                TRUE
10:                                      NA                                      NA                               TRUE                       NA                                TRUE
11:                                      NA                                      NA                                 NA                       NA                                  NA
12:                                      NA                                      NA                                 NA                       NA                                  NA
13:                                      NA                                      NA                               TRUE                       NA                                TRUE
14:                                      NA                                      NA                               TRUE                       NA                                TRUE
15:                                      NA                                    TRUE                                 NA                       NA                                  NA
16:                                      NA                                      NA                               TRUE                     TRUE                                TRUE
17:                                      NA                                      NA                                 NA                     TRUE                                  NA
18:                                      NA                                      NA                                 NA                     TRUE                                TRUE
19:                                      NA                                      NA                                 NA                       NA                                  NA
20:                                      NA                                      NA                               TRUE                       NA                                  NA
21:                                      NA                                      NA                                 NA                       NA                                  NA
22:                                      NA                                      NA                                 NA                       NA                                  NA
23:                                      NA                                      NA                               TRUE                     TRUE                                  NA
24:                                      NA                                    TRUE                                 NA                       NA                                  NA
25:                                      NA                                      NA                                 NA                       NA                                  NA
26:                                      NA                                      NA                               TRUE                     TRUE                                TRUE
27:                                      NA                                      NA                               TRUE                     TRUE                                  NA
28:                                      NA                                      NA                                 NA                       NA                                  NA
29:                                      NA                                      NA                                 NA                       NA                                  NA
30:                                      NA                                      NA                               TRUE                       NA                                  NA
31:                                      NA                                    TRUE                                 NA                       NA                                  NA
32:                                      NA                                    TRUE                                 NA                       NA                                  NA
33:                                    TRUE                                      NA                               TRUE                     TRUE                                TRUE
34:                                    TRUE                                    TRUE                                 NA                       NA                                  NA
35:                                    TRUE                                    TRUE                               TRUE                     TRUE                                TRUE
36:                                      NA                                      NA                                 NA                       NA                                  NA
37:                                      NA                                      NA                                 NA                       NA                                  NA
38:                                      NA                                    TRUE                                 NA                       NA                                  NA
39:                                    TRUE                                      NA                                 NA                       NA                                  NA
40:                                      NA                                      NA                               TRUE                       NA                                  NA
41:                                    TRUE                                      NA                                 NA                       NA                                  NA
42:                                    TRUE                                      NA                                 NA                       NA                                  NA
43:                                      NA                                      NA                               TRUE                       NA                                  NA
44:                                    TRUE                                    TRUE                                 NA                       NA                                TRUE
45:                                      NA                                      NA                                 NA                       NA                                  NA
46:                                      NA                                      NA                               TRUE                     TRUE                                TRUE
47:                                    TRUE                                      NA                                 NA                       NA                                  NA
48:                                      NA                                      NA                               TRUE                       NA                                  NA
49:                                      NA                                      NA                                 NA                       NA                                  NA
50:                                      NA                                      NA                                 NA                       NA                                  NA
    primary_cortical_neuron_DIV10_Tc1_K primary_cortical_neuron_DIV4_CD1_PDS ESC_derived_neuron_CD1_PDS primary_cortical_neuron_DIV10_CD1_PDS primary_cortical_neuron_DIV10_Tc1_PDS V2.y
 1:                                  NA                                   NA                         NA                                    NA                                    NA   11
 2:                                  NA                                 TRUE                       TRUE                                  TRUE                                  TRUE    8
 3:                                  NA                                   NA                       TRUE                                    NA                                    NA    9
 4:                                  NA                                 TRUE                         NA                                    NA                                    NA   11
 5:                                  NA                                 TRUE                       TRUE                                  TRUE                                    NA    3
 6:                                  NA                                   NA                       TRUE                                    NA                                  TRUE   10
 7:                                  NA                                 TRUE                       TRUE                                  TRUE                                    NA    9
 8:                                  NA                                   NA                         NA                                    NA                                  TRUE   11
 9:                                TRUE                                 TRUE                       TRUE                                  TRUE                                  TRUE    4
10:                                TRUE                                 TRUE                         NA                                  TRUE                                  TRUE    6
11:                                  NA                                 TRUE                         NA                                  TRUE                                    NA   10
12:                                  NA                                 TRUE                         NA                                  TRUE                                  TRUE    9
13:                                  NA                                 TRUE                         NA                                  TRUE                                    NA    8
14:                                TRUE                                 TRUE                         NA                                  TRUE                                  TRUE    6
15:                                  NA                                   NA                         NA                                    NA                                  TRUE   10
16:                                  NA                                   NA                         NA                                    NA                                    NA    9
17:                                  NA                                   NA                       TRUE                                    NA                                    NA    9
18:                                  NA                                   NA                       TRUE                                  TRUE                                    NA    8
19:                                  NA                                 TRUE                         NA                                    NA                                    NA   11
20:                                  NA                                 TRUE                         NA                                    NA                                    NA    9
21:                                  NA                                 TRUE                         NA                                    NA                                    NA   11
22:                                  NA                                 TRUE                       TRUE                                  TRUE                                  TRUE    8
23:                                TRUE                                 TRUE                       TRUE                                    NA                                  TRUE    6
24:                                  NA                                   NA                         NA                                    NA                                    NA   11
25:                                  NA                                 TRUE                       TRUE                                    NA                                  TRUE    9
26:                                TRUE                                 TRUE                       TRUE                                  TRUE                                  TRUE    4
27:                                  NA                                 TRUE                       TRUE                                    NA                                    NA    6
28:                                  NA                                   NA                         NA                                    NA                                    NA   10
29:                                  NA                                 TRUE                       TRUE                                  TRUE                                  TRUE    8
30:                                  NA                                 TRUE                         NA                                    NA                                    NA    9
31:                                  NA                                   NA                         NA                                    NA                                  TRUE   10
32:                                TRUE                                   NA                         NA                                    NA                                  TRUE    9
33:                                  NA                                   NA                         NA                                    NA                                    NA    6
34:                                  NA                                   NA                         NA                                    NA                                    NA   10
35:                                TRUE                                   NA                         NA                                    NA                                    NA    4
36:                                  NA                                   NA                       TRUE                                    NA                                    NA   11
37:                                TRUE                                   NA                         NA                                    NA                                  TRUE   10
38:                                  NA                                 TRUE                         NA                                    NA                                  TRUE    8
39:                                  NA                                 TRUE                         NA                                  TRUE                                    NA    8
40:                                TRUE                                 TRUE                         NA                                    NA                                  TRUE    8
41:                                  NA                                   NA                         NA                                    NA                                    NA   11
42:                                  NA                                   NA                         NA                                  TRUE                                    NA   10
43:                                  NA                                 TRUE                         NA                                    NA                                    NA   10
44:                                TRUE                                   NA                         NA                                    NA                                    NA    8
45:                                  NA                                 TRUE                         NA                                  TRUE                                    NA   10
46:                                TRUE                                 TRUE                       TRUE                                  TRUE                                  TRUE    4
47:                                  NA                                 TRUE                       TRUE                                  TRUE                                    NA    6
48:                                  NA                                 TRUE                         NA                                    NA                                    NA   10
49:                                  NA                                   NA                         NA                                  TRUE                                    NA   11
50:                                  NA                                 TRUE                         NA                                    NA                                    NA   11
 [ reached getOption("max.print") -- omitted 3 rows ]

KCL_human_CE[, ID:=paste( chrom, strand, start, end  , sep="_")]
All_human.mouse.diff.gene <- merge(All_human.mouse.diff, KCL_human_CE, by="ID")
View(All_human.mouse.diff.gene[order(V2.y, V2.x  )][, c("ID", "mID", "V2.x", "V2.y", "wikigene_description", "hgnc_symbol")] )
cat(All_human.mouse.diff.gene[, hgnc_symbol], sep="\n")

ADGRA1
CCSER2
SIDT2
NAV2
PCSK7
AMBRA1
HNRNPUL2
HNRNPUL2
HNRNPUL2-BSCL2
HNRNPUL2-BSCL2
NRXN2
PRPF40B
TARBP2
NAB2
ABCD4
TNRC6A
TBC1D24
ATXN2L
INO80E
FBRS
FBRS
ZNF263
FBXL16
NLGN2
UBTF
MBD1
ACTN4
ACTN4
CAMSAP3
UNC13A
PIP5K1C
SLC6A17
TXLNA
MAP7D1
ADGRL2
SEMA6C
PI4KB
MEF2D
MED8
CHD5
RBCK1
MTMR3
OSBPL6
BIN1
EIF4G1
FAM131A
CSRNP1
CELSR3
GPBP1
SRRT
ZMIZ2
CLIP2
SH3GLB2
RBM10

fwrite(All_human.mouse.diff.gene[order(V2.y, V2.x  )][, c("ID", "V2.x", "V2.y", "wikigene_description", "hgnc_symbol")], "../potassium_experiments/human.mouse.diff.G4.gene.txt",  na="FALSE", sep = "\t", quote=F)

KCL_human[ID=""]

Error in `[.data.table`(KCL_human, ID = "") : unused argument (ID = "")

total_mouse_PDS_ME_table[G4_bol=="With G-quadruplex", mean(exon_len) ]

Error in mean(exon_len) : object 'exon_len' not found

primary_cortical_neuron_DIV4_CD1_K_ME_table <- diff_G4_ME_table("../KCL/MicroExonator/closest/primary_cortical_neuron_DIV4_CD1.diff.upstream.G4seq_K" , "../KCL/MicroExonator/closest/primary_cortical_neuron_DIV4_CD1.diff.downstream.G4seq_K", 100 )
primary_cortical_neuron_DIV4_CD1_K_ME_table.2x2 <- matrix(ncol = 2,
c(nrow(primary_cortical_neuron_DIV4_CD1_K_ME_table[ exon_class=="exon" & G4_bol=="Without G-quadruplex"]),
nrow(primary_cortical_neuron_DIV4_CD1_K_ME_table[ exon_class=="exon" & G4_bol=="With G-quadruplex"]),
nrow(primary_cortical_neuron_DIV4_CD1_K_ME_table[ exon_class=="microexon" & G4_bol=="Without G-quadruplex"]),
nrow(primary_cortical_neuron_DIV4_CD1_K_ME_table[ exon_class=="microexon" & G4_bol=="With G-quadruplex"]) ))
chisq.test( primary_cortical_neuron_DIV4_CD1_K_ME_table.2x2)

    Pearson's Chi-squared test with Yates' continuity correction

data:  primary_cortical_neuron_DIV4_CD1_K_ME_table.2x2
X-squared = 2.0509, df = 1, p-value = 0.1521

primary_cortical_neuron_DIV4_CD1_PDS_ME_table <- diff_G4_ME_table("../KCL/MicroExonator/closest/primary_cortical_neuron_DIV4_CD1.diff.upstream.G4seq_PDS" , "../KCL/MicroExonator/closest/primary_cortical_neuron_DIV4_CD1.diff.downstream.G4seq_PDS", 100 )
primary_cortical_neuron_DIV4_CD1_PDS_ME_table.2x2 <- matrix(ncol = 2,
c(nrow(primary_cortical_neuron_DIV4_CD1_PDS_ME_table[ exon_class=="exon" & G4_bol=="Without G-quadruplex"]),
nrow(primary_cortical_neuron_DIV4_CD1_PDS_ME_table[ exon_class=="exon" & G4_bol=="With G-quadruplex"]),
nrow(primary_cortical_neuron_DIV4_CD1_PDS_ME_table[ exon_class=="microexon" & G4_bol=="Without G-quadruplex"]),
nrow(primary_cortical_neuron_DIV4_CD1_PDS_ME_table[ exon_class=="microexon" & G4_bol=="With G-quadruplex"]) ))
chisq.test( primary_cortical_neuron_DIV4_CD1_PDS_ME_table.2x2)

    Pearson's Chi-squared test with Yates' continuity correction

data:  primary_cortical_neuron_DIV4_CD1_PDS_ME_table.2x2
X-squared = 1.0594, df = 1, p-value = 0.3034

Control_vs_KCL_K_ME_table <- diff_G4_ME_table("../KCL/MicroExonator/closest/Control_vs_KCL.diff.upstream.G4seq_K" , "../KCL/MicroExonator/closest/Control_vs_KCL.diff.downstream.G4seq_K", 100 )
Control_vs_KCL_K_ME_table.2x2 <- matrix(ncol = 2,
c(nrow(Control_vs_KCL_K_ME_table[ exon_class=="exon" & G4_bol=="Without G-quadruplex"]),
nrow(Control_vs_KCL_K_ME_table[ exon_class=="exon" & G4_bol=="With G-quadruplex"]),
nrow(Control_vs_KCL_K_ME_table[ exon_class=="microexon" & G4_bol=="Without G-quadruplex"]),
nrow(Control_vs_KCL_K_ME_table[ exon_class=="microexon" & G4_bol=="With G-quadruplex"]) ))
chisq.test( Control_vs_KCL_K_ME_table.2x2)

    Pearson's Chi-squared test with Yates' continuity correction

data:  Control_vs_KCL_K_ME_table.2x2
X-squared = 0.026068, df = 1, p-value = 0.8717

Control_vs_KCL_PDS_ME_table <- diff_G4_ME_table("../KCL/MicroExonator/closest/Control_vs_KCL.diff.upstream.G4seq_PDS" , "../KCL/MicroExonator/closest/Control_vs_KCL.diff.downstream.G4seq_K", 100 )
Control_vs_KCL_PDS_ME_table.2x2 <- matrix(ncol = 2,
c(nrow(Control_vs_KCL_PDS_ME_table[ exon_class=="exon" & G4_bol=="Without G-quadruplex"]),
nrow(Control_vs_KCL_PDS_ME_table[ exon_class=="exon" & G4_bol=="With G-quadruplex"]),
nrow(Control_vs_KCL_PDS_ME_table[ exon_class=="microexon" & G4_bol=="Without G-quadruplex"]),
nrow(Control_vs_KCL_PDS_ME_table[ exon_class=="microexon" & G4_bol=="With G-quadruplex"]) ))
chisq.test( Control_vs_KCL_PDS_ME_table.2x2)

    Pearson's Chi-squared test with Yates' continuity correction

data:  Control_vs_KCL_PDS_ME_table.2x2
X-squared = 10.324, df = 1, p-value = 0.001313

splice_node_dot_plot3 <- function(upstream.path, downstream.path, dist_lim ) {
KCL_x_upstream <- fread(upstream.path  )
colnames(KCL_x_upstream) <- c("w.chrom", "w.start", "w.end", "w.strand", "chrom", "start", "end", "strand", "Type", "Psi_A", "Psi_B", "DeltaPsi", "Probability", "gchrom", "gstart", "gend", "gscore", "exon_dist"  )
KCL_x_upstream[ ,dist:=abs(w.start - (gstart + (gend- gstart)/2)) ]
KCL_x_downstream<- fread(downstream.path  )
colnames(KCL_x_downstream) <- c("w.chrom", "w.start", "w.end", "w.strand", "chrom", "start", "end", "strand", "Type", "Psi_A", "Psi_B", "DeltaPsi", "Probability", "gchrom", "gstart", "gend", "gscore", "exon_dist"  )
KCL_x_downstream[ ,dist:=abs(w.start - (gstart + (gend- gstart)/2)) ]
KCL_x <-  merge(KCL_x_upstream[, c("chrom",  "start", "end", "strand",  "Type" ,  "DeltaPsi", "Probability", "dist") ],
                    KCL_x_downstream[, c("chrom",  "start", "end", "strand",  "Type" ,  "DeltaPsi", "Probability", "dist") ], 
                    by=c("chrom",  "start", "end", "strand",  "Type" ,  "DeltaPsi", "Probability") )
#KCL_x <-  KCL_x[end-start>30 || Type!="CE", ]
KCL_x[(dist.x<=dist_lim | dist.y<=dist_lim ), G4_bol:="With G-quadruplex"]
KCL_x[(dist.x>dist_lim & dist.y>dist_lim ), G4_bol:="Without G-quadruplex"]
KCL_x$G4_bol <- factor(KCL_x$G4_bol, levels=c("Without G-quadruplex", "With G-quadruplex") )
KCL_x[  , diff:="NA"]
KCL_x[ (DeltaPsi<=-0.1 & Probability>=0.90) , diff:="In"]
KCL_x[ (DeltaPsi>0.1 & Probability>=0.90) , diff:="Ex"]
KCL_x_stats <- merge(KCL_x[  G4_bol=="Without G-quadruplex",  .(WO_G4=.N) , by=c("Type", "diff")  ], 
KCL_x[  G4_bol=="With G-quadruplex",  .(W_G4=.N) , by=c("Type", "diff")  ],
by=c("Type", "diff"))
KCL_x_stats <- merge(KCL_x_stats[diff!="NA"],  KCL_x_stats[diff=="NA" , .(Type,  WO_G4_NA=WO_G4, W_G4_NA=W_G4) ], by="Type")
KCL_x_stats[, `:=`(WO_G4_fraq=WO_G4/WO_G4_NA, W_G4_fraq=W_G4/W_G4_NA)]
KCL_x_stats[ , OR := W_G4_fraq/WO_G4_fraq]
KCL_x_stats.chi <- data.table()
for ( i in unique(KCL_x_stats[Type!="AL"]$Type)){
  
matrix.ex <-  matrix(nrow=2, c(KCL_x_stats[Type==i & diff=="Ex"]$WO_G4_NA, KCL_x_stats[Type==i & diff=="Ex"]$WO_G4, KCL_x_stats[Type==i & diff=="Ex"]$W_G4_NA, KCL_x_stats[Type==i & diff=="Ex"]$W_G4))
matrix.ex_res <- chisq.test(matrix.ex, correct=TRUE)
matrix.in <-  matrix(nrow=2, c(KCL_x_stats[Type==i & diff=="In"]$WO_G4_NA, KCL_x_stats[Type==i & diff=="In"]$WO_G4, KCL_x_stats[Type==i & diff=="In"]$W_G4_NA, KCL_x_stats[Type==i & diff=="In"]$W_G4))
matrix.in_res <- chisq.test(matrix.in, correct=TRUE)
KCL_x_stats.chi <- rbind(KCL_x_stats.chi, cbind(i, "Ex", matrix.ex_res$p.value)) 
KCL_x_stats.chi <- rbind(KCL_x_stats.chi, cbind(i, "In", matrix.in_res$p.value)) 
                                                        
}
colnames(KCL_x_stats.chi) <- c("Type", "diff", "P_value")
ntest = nrow(KCL_x_stats.chi)
KCL_x_stats.chi[ , `:=`(P_value.Bonferroni=as.numeric(P_value)*ntest) ]
KCL_x_stats <- merge(KCL_x_stats, KCL_x_stats.chi, by=c("Type", "diff"))
ggplot(KCL_x_stats) +
  geom_point(aes(Type, diff, size = -log(P_value.Bonferroni), shape=P_value.Bonferroni<0.05, colour=log2(OR) ) ) +
  scale_colour_gradient2(low="blue", high="red", mid = "grey", midpoint = 0) +
  theme_bw() +
      theme(legend.position = "top", legend.direction = "horizontal") 
return(KCL_x_stats)
}

human.dotplot <- splice_node_dot_plot2("../KCL/MicroExonator/Control_vs_KCL.diff.upstream_100nt.G4s",  "../KCL/MicroExonator/Control_vs_KCL.diff.downstream_100nt.G4s"  )



human.motif <- splice_node_dot_plot3("../KCL/MicroExonator/closest/Control_vs_KCL.diff.upstream.G4s",
                                        "../KCL/MicroExonator/closest/Control_vs_KCL.diff.downstream.G4s",
                                        100)




human.K <- splice_node_dot_plot3("../KCL/MicroExonator/closest/Control_vs_KCL.diff.upstream.G4seq_K",
                                        "../KCL/MicroExonator/closest/Control_vs_KCL.diff.downstream.G4seq_K",
                                        45)


human.PDS <- splice_node_dot_plot3("../KCL/MicroExonator/closest/Control_vs_KCL.diff.upstream.G4seq_PDS",
                                        "../KCL/MicroExonator/closest/Control_vs_KCL.diff.downstream.G4seq_PDS",
                                   45)


human.motif[ , G4_signal:="Motif"  ]
human.K[ , G4_signal:="K+"  ]
human.PDS[ , G4_signal:="PDS"  ]

human.motif_K_PDS <- rbind(human.motif, human.K, human.PDS)

human.motif_K_PDS$G4_signal <- factor(human.motif_K_PDS$G4_signal, levels = c("Motif", "K+", "PDS") )

Fig5.A1 <- ggplot(human.motif_K_PDS) +
  geom_point(aes(Type, diff, size = -log10(P_value.Bonferroni), shape=P_value.Bonferroni<0.05, colour=log2(OR) ) ) +
  scale_colour_gradient2(low="blue", high="red", mid = "grey", midpoint = 0) +
  facet_grid(G4_signal ~ .) +
  theme_bw() +
      theme(legend.position = "top", legend.direction = "horizontal")


Fig5.A1

supp.dotplot.A <- splice_node_dot_plot2("../KCL/MicroExonator/ESC-derived_neuron_CD1.diff.upstream_100nt.G4s",  "../KCL/MicroExonator/ESC-derived_neuron_CD1.diff.downstream_100nt.G4s"  )
ESC_derived_neuron_CD1.motif <- splice_node_dot_plot3("../KCL/MicroExonator/closest/ESC-derived_neuron_CD1.diff.upstream.G4s.fix",
                                        "../KCL/MicroExonator/closest/ESC-derived_neuron_CD1.diff.downstream.G4s.fix",
                                        100)

Chi-squared approximation may be incorrect

ESC_derived_neuron_CD1.K <- splice_node_dot_plot3("../KCL/MicroExonator/closest/ESC-derived_neuron_CD1.diff.upstream.G4seq_K",
                                        "../KCL/MicroExonator/closest/ESC-derived_neuron_CD1.diff.downstream.G4seq_K",
                                        45)

Chi-squared approximation may be incorrectChi-squared approximation may be incorrectChi-squared approximation may be incorrectChi-squared approximation may be incorrectChi-squared approximation may be incorrect

ESC_derived_neuron_CD1.PDS <- splice_node_dot_plot3("../KCL/MicroExonator/closest/ESC-derived_neuron_CD1.diff.upstream.G4seq_PDS",
                                        "../KCL/MicroExonator/closest/ESC-derived_neuron_CD1.diff.downstream.G4seq_PDS",
                                        45)
ESC_derived_neuron_CD1.motif[ , G4_signal:="Motif"  ]
ESC_derived_neuron_CD1.K[ , G4_signal:="K+"  ]
ESC_derived_neuron_CD1.PDS[ , G4_signal:="PDS"  ]
ESC_derived_neuron_CD1.motif_K_PDS <- rbind(ESC_derived_neuron_CD1.motif, ESC_derived_neuron_CD1.K, ESC_derived_neuron_CD1.PDS)
ESC_derived_neuron_CD1.motif_K_PDS$G4_signal <- factor(ESC_derived_neuron_CD1.motif_K_PDS$G4_signal, levels = c("Motif", "K+", "PDS") )
ggplot(ESC_derived_neuron_CD1.motif_K_PDS) +
  geom_point(aes(Type, diff, size = -log10(P_value.Bonferroni), shape=P_value.Bonferroni<0.05, colour=log2(OR) ) ) +
  scale_colour_gradient2(low="blue", high="red", mid = "grey", midpoint = 0) +
  facet_grid(G4_signal ~ .) +
  ylab("") +
  theme_bw() +
      theme(legend.position = "top", legend.direction = "horizontal") 

supp.dotplot.C <-  splice_node_dot_plot2("../KCL/MicroExonator/primary_cortical_neuron_DIV10_CD1.diff.upstream_100nt.G4s",  "../KCL/MicroExonator/primary_cortical_neuron_DIV10_CD1.diff.downstream_100nt.G4s"  )
primary_cortical_neuron_DIV10_CD1.motif <- splice_node_dot_plot3("../KCL/MicroExonator/closest/primary_cortical_neuron_DIV10_CD1.diff.upstream.G4s.fix",
                                        "../KCL/MicroExonator/closest/primary_cortical_neuron_DIV10_CD1.diff.downstream.G4s.fix",
                                        100)
primary_cortical_neuron_DIV10_CD1.K <- splice_node_dot_plot3("../KCL/MicroExonator/closest/primary_cortical_neuron_DIV10_CD1.diff.upstream.G4seq_K",
                                        "../KCL/MicroExonator/closest/primary_cortical_neuron_DIV10_CD1.diff.downstream.G4seq_K",
                                        45)

Chi-squared approximation may be incorrectChi-squared approximation may be incorrectChi-squared approximation may be incorrect

primary_cortical_neuron_DIV10_CD1.PDS <- splice_node_dot_plot3("../KCL/MicroExonator/closest/primary_cortical_neuron_DIV10_CD1.diff.upstream.G4seq_PDS",
                                        "../KCL/MicroExonator/closest/primary_cortical_neuron_DIV10_CD1.diff.downstream.G4seq_PDS",
                                        45)
primary_cortical_neuron_DIV10_CD1.motif[ , G4_signal:="Motif"  ]
primary_cortical_neuron_DIV10_CD1.K[ , G4_signal:="K+"  ]
primary_cortical_neuron_DIV10_CD1.PDS[ , G4_signal:="PDS"  ]
primary_cortical_neuron_DIV10_CD1.motif_K_PDS <- rbind(primary_cortical_neuron_DIV10_CD1.motif, primary_cortical_neuron_DIV10_CD1.K, primary_cortical_neuron_DIV10_CD1.PDS)
primary_cortical_neuron_DIV10_CD1.motif_K_PDS$G4_signal <- factor(primary_cortical_neuron_DIV10_CD1.motif_K_PDS$G4_signal, levels = c("Motif", "K+", "PDS") )
ggplot(primary_cortical_neuron_DIV10_CD1.motif_K_PDS) +
  geom_point(aes(Type, diff, size = -log10(P_value.Bonferroni), shape=P_value.Bonferroni<0.05, colour=log2(OR) ) ) +
  scale_colour_gradient2(low="blue", high="red", mid = "grey", midpoint = 0) +
  facet_grid(G4_signal ~ .) +
  ylab("") +
  theme_bw() +
      theme(legend.position = "top", legend.direction = "horizontal") 

supp.dotplot.D <- splice_node_dot_plot2("../KCL/MicroExonator/primary_cortical_neuron_DIV10_Tc1.diff.upstream_100nt.G4s",  "../KCL/MicroExonator/primary_cortical_neuron_DIV10_Tc1.diff.downstream_100nt.G4s"  )
primary_cortical_neuron_DIV10_Tc1.motif <- splice_node_dot_plot3("../KCL/MicroExonator/closest/primary_cortical_neuron_DIV10_Tc1.diff.upstream.G4s.fix",
                                        "../KCL/MicroExonator/closest/primary_cortical_neuron_DIV10_Tc1.diff.downstream.G4s.fix",
                                        100)
primary_cortical_neuron_DIV10_Tc1.K <- splice_node_dot_plot3("../KCL/MicroExonator/closest/primary_cortical_neuron_DIV10_Tc1.diff.upstream.G4seq_K",
                                        "../KCL/MicroExonator/closest/primary_cortical_neuron_DIV10_Tc1.diff.downstream.G4seq_K",
                                        45)
primary_cortical_neuron_DIV10_Tc1.PDS <- splice_node_dot_plot3("../KCL/MicroExonator/closest/primary_cortical_neuron_DIV10_Tc1.diff.upstream.G4seq_PDS",
                                        "../KCL/MicroExonator/closest/primary_cortical_neuron_DIV10_Tc1.diff.downstream.G4seq_PDS",
                                        45)
primary_cortical_neuron_DIV10_Tc1.motif[ , G4_signal:="Motif"  ]
primary_cortical_neuron_DIV10_Tc1.K[ , G4_signal:="K+"  ]
primary_cortical_neuron_DIV10_Tc1.PDS[ , G4_signal:="PDS"  ]
primary_cortical_neuron_DIV10_Tc1.motif_K_PDS <- rbind(primary_cortical_neuron_DIV10_Tc1.motif, primary_cortical_neuron_DIV10_Tc1.K, primary_cortical_neuron_DIV10_Tc1.PDS)
primary_cortical_neuron_DIV10_Tc1.motif_K_PDS$G4_signal <- factor(primary_cortical_neuron_DIV10_Tc1.motif_K_PDS$G4_signal, levels = c("Motif", "K+", "PDS") )
ggplot(primary_cortical_neuron_DIV10_Tc1.motif_K_PDS) +
  geom_point(aes(Type, diff, size = -log10(P_value.Bonferroni), shape=P_value.Bonferroni<0.05, colour=log2(OR) ) ) +
  scale_colour_gradient2(low="blue", high="red", mid = "grey", midpoint = 0) +
  facet_grid(G4_signal ~ .) +
  ylab("") +
  theme_bw() +
      theme(legend.position = "top", legend.direction = "horizontal") 

supp.dotplot.B <- splice_node_dot_plot2("../KCL/MicroExonator/primary_cortical_neuron_DIV4_CD1.diff.upstream_100nt.G4s",  "../KCL/MicroExonator/primary_cortical_neuron_DIV4_CD1.diff.downstream_100nt.G4s"  )
primary_cortical_neuron_DIV4_CD1.motif <- splice_node_dot_plot3("../KCL/MicroExonator/closest/primary_cortical_neuron_DIV4_CD1.diff.upstream.G4s.fix",
                                        "../KCL/MicroExonator/closest/primary_cortical_neuron_DIV4_CD1.diff.downstream.G4s.fix",
                                        100)
primary_cortical_neuron_DIV4_CD1.K <- splice_node_dot_plot3("../KCL/MicroExonator/closest/primary_cortical_neuron_DIV4_CD1.diff.upstream.G4seq_K",
                                        "../KCL/MicroExonator/closest/primary_cortical_neuron_DIV4_CD1.diff.downstream.G4seq_K",
                                        45)

Chi-squared approximation may be incorrect

primary_cortical_neuron_DIV4_CD1.PDS <- splice_node_dot_plot3("../KCL/MicroExonator/closest/primary_cortical_neuron_DIV4_CD1.diff.upstream.G4seq_PDS",
                                        "../KCL/MicroExonator/closest/primary_cortical_neuron_DIV4_CD1.diff.downstream.G4seq_PDS",
                                        45)
primary_cortical_neuron_DIV4_CD1.motif[ , G4_signal:="Motif"  ]
primary_cortical_neuron_DIV4_CD1.K[ , G4_signal:="K+"  ]
primary_cortical_neuron_DIV4_CD1.PDS[ , G4_signal:="PDS"  ]
primary_cortical_neuron_DIV4_CD1.motif_K_PDS <- rbind(primary_cortical_neuron_DIV4_CD1.motif, primary_cortical_neuron_DIV4_CD1.K, primary_cortical_neuron_DIV4_CD1.PDS)
primary_cortical_neuron_DIV4_CD1.motif_K_PDS$G4_signal <- factor(primary_cortical_neuron_DIV4_CD1.motif_K_PDS$G4_signal, levels = c("Motif", "K+", "PDS") )
ggplot(primary_cortical_neuron_DIV4_CD1.motif_K_PDS) +
  geom_point(aes(Type, diff, size = -log10(P_value.Bonferroni), shape=P_value.Bonferroni<0.05, colour=log2(OR) ) ) +
  scale_colour_gradient2(low="blue", high="red", mid = "grey", midpoint = 0) +
  facet_grid(G4_signal ~ .) +
  ylab("") +
  theme_bw() +
      theme(legend.position = "top", legend.direction = "horizontal") 

KCL_human[(DeltaPsi<=-0.1 & Probability>0.9), Delta_type:="Included"]
KCL_human[(DeltaPsi>=0.1 & Probability>0.9), Delta_type:="Skiped"]
KCL_human[is.na(Delta_type), Delta_type:="None"]
KCL_human_stats <-  KCL_human[Type=="CE" , .(count=.N), by=c("Delta_type", "exon", "G4_bol") ] 
KCL_human_stats[, total:=sum(count), by="G4_bol"]
KCL_human_stats[, fraction:=count/total]
Fig5.B <- ggplot() +
  geom_bar(data=KCL_human_stats[Delta_type!="None" & exon=="exon", ] , aes(x= G4_bol, y=fraction, group=Delta_type, fill=Delta_type ) , position="dodge", stat="identity"  ) +
  xlab("") +
  ylab("Fraction of differentially inclued exons ") +
  theme_bw() +
  guides(fill=guide_legend(title="Alternative splicing event")) +
    theme(legend.position = "top", legend.direction = "horizontal") 
Fig5.B

diff.up <- read_dist_table("~/Google_Drive/Results/Non_B/KCL/SS_enrichment/Control_vs_KCL.diff_upstream_prob_0_9.bed.score.All_G4.tsv.clean.txt..bed.list.out.num")

Parsed with column specification:
cols(
  .default = col_double()
)
See spec(...) for full column specifications.
1 parsing failure.
row col     expected       actual                                                                                                                                    file
  2  -- 2001 columns 2002 columns '~/Google_Drive/Results/Non_B/KCL/SS_enrichment/Control_vs_KCL.diff_upstream_prob_0_9.bed.score.All_G4.tsv.clean.txt..bed.list.out.num'

diff.down <- read_dist_table("~/Google_Drive/Results/Non_B/KCL/SS_enrichment/Control_vs_KCL.diff_downstream_prob_0_9.bed.score.All_G4.tsv.clean.txt..bed.list.out.num")

Parsed with column specification:
cols(
  .default = col_double()
)
See spec(...) for full column specifications.
1 parsing failure.
row col     expected       actual                                                                                                                                      file
  2  -- 2001 columns 2002 columns '~/Google_Drive/Results/Non_B/KCL/SS_enrichment/Control_vs_KCL.diff_downstream_prob_0_9.bed.score.All_G4.tsv.clean.txt..bed.list.out.num'

eql.up <- read_dist_table("~/Google_Drive/Results/Non_B/KCL/SS_enrichment/Control_vs_KCL.diff_upstream_less.bed.score.All_G4.tsv.clean.txt..bed.list.out.num")

Parsed with column specification:
cols(
  .default = col_double()
)
See spec(...) for full column specifications.
1 parsing failure.
row col     expected       actual                                                                                                                                file
  2  -- 2001 columns 2002 columns '~/Google_Drive/Results/Non_B/KCL/SS_enrichment/Control_vs_KCL.diff_upstream_less.bed.score.All_G4.tsv.clean.txt..bed.list.out.num'

eql.down <- read_dist_table("~/Google_Drive/Results/Non_B/KCL/SS_enrichment/Control_vs_KCL.diff_downstream_less.bed.score.All_G4.tsv.clean.txt..bed.list.out.num")

Parsed with column specification:
cols(
  .default = col_double()
)
See spec(...) for full column specifications.
1 parsing failure.
row col     expected       actual                                                                                                                                  file
  2  -- 2001 columns 2002 columns '~/Google_Drive/Results/Non_B/KCL/SS_enrichment/Control_vs_KCL.diff_downstream_less.bed.score.All_G4.tsv.clean.txt..bed.list.out.num'

diff.up[, `:=`(type="diff", pos="up" )]
diff.down[, `:=`(type="diff", pos="down" )]
eql.up[, `:=`(type="eql", pos="up" )]
eql.down[, `:=`(type="eql", pos="down" )]
diff_eql <-  rbind(diff.up,  diff.down, eql.up, eql.down)
ggplot(diff_eql) +
  geom_line(aes(x=Position, y=Enrrichment, group=type)) +
  facet_grid(pos ~ .) +
  theme_bw() 

plot_eql_diff <- function(eql_up_plus, eql_up_minus, eql_down_plus, eql_down_minus, diff_up_plus, diff_up_minus, diff_down_plus, diff_down_minus   ){ 
diff.up_plus <- read_dist_table(diff_up_plus)
diff.up_minus <- read_dist_table(diff_up_minus)
diff.down_plus <- read_dist_table(diff_down_plus)
diff.down_minus <- read_dist_table(diff_down_minus)
diff.up_minus[,Position:=Position*-1]
diff.down_minus[,Position:=Position*-1]
diff.TOTAL <- plot_density(diff.up_plus, diff.up_minus, diff.down_plus, diff.down_minus)
eql.up_plus <- read_dist_table(eql_up_plus)
eql.up_minus <- read_dist_table(eql_up_minus)
eql.down_plus <- read_dist_table(eql_down_plus)
eql.down_minus <- read_dist_table(eql_down_minus)
eql.up_minus[,Position:=Position*-1]
eql.down_minus[,Position:=Position*-1]
eql.TOTAL <- plot_density(eql.up_plus, eql.up_minus, eql.down_plus, eql.down_minus)
diff.TOTAL[, type:="diff"]
eql.TOTAL[, type:="eql"]
diff_eql.TOTAL <- rbind(diff.TOTAL, eql.TOTAL)
ggplot(diff_eql.TOTAL) +
  geom_line(aes(x=Position, y=Enrrichment, color=type)) +
  xlim(c(-250,250)) +
  facet_grid(. ~ exon_pos  ) +
  labs(colour = "Potassium effect") +
  theme_bw() +
  theme(legend.position = "top", legend.direction = "horizontal") 
}

ggplot(diff_eql.TOTAL) +
  geom_line(aes(x=Position, y=Enrrichment, color=type)) +
   geom_ribbon(aes(ymin=Enrrichment_l, ymax=Enrrichment_u, x=Position, fill=type), alpha=0.3 )+
  xlim(c(-250,250)) +
  facet_grid(. ~ exon_pos  ) +
  labs(colour = "Potassium effect") +
  theme_bw() +
  theme(legend.position = "top", legend.direction = "horizontal") +
  scale_fill_manual(values=c("#669900", "grey")) +  
  scale_color_manual(values=c("#669900", "darkgrey"))

Error in FUN(X[[i]], ...) : object 'Enrrichment_l' not found

KCL_human <- fread("../KCL/MicroExonator/Control_vs_KCL.diff", sep="\t")

Detected 11 column names but the data has 12 columns (i.e. invalid file). Added 1 extra default column name for the first column which is guessed to be row names or an index. Use setnames() afterwards if this guess is not correct, or fix the file write command that created the file to create a valid file.

KCL_human <- KCL_human[, 1:11]
colnames(KCL_human) <- c("Gene","Node", "Coord", "Strand", "Type", "Psi_A", "Psi_B", "DeltaPsi", "Probability", "Complexity", "Entropy")
human.CE.NA <- nrow(KCL_human[(abs(DeltaPsi)<0.1 | Probability<0.9)  &  Type=="CE"])
human.CE.diff <- nrow(KCL_human[abs(DeltaPsi)>=0.1 & Probability>=0.9 &  Type=="CE"])
KCL_ESC_derived_neuron_CD1 <- fread("../KCL/MicroExonator/ESC-derived_neuron_CD1.diff", sep="\t")

Detected 11 column names but the data has 12 columns (i.e. invalid file). Added 1 extra default column name for the first column which is guessed to be row names or an index. Use setnames() afterwards if this guess is not correct, or fix the file write command that created the file to create a valid file.

KCL_ESC_derived_neuron_CD1  <- KCL_ESC_derived_neuron_CD1 [, 1:11]
colnames(KCL_ESC_derived_neuron_CD1 ) <- c("Gene","Node", "Coord", "Strand", "Type", "Psi_A", "Psi_B", "DeltaPsi", "Probability", "Complexity", "Entropy")
ESC_derived_neuron_CD1.CE.NA <- nrow(KCL_ESC_derived_neuron_CD1 [(abs(DeltaPsi)<0.1 | Probability<0.9)  &  Type=="CE"])
ESC_derived_neuron_CD1.CE.diff <- nrow(KCL_ESC_derived_neuron_CD1[abs(DeltaPsi)>=0.1 & Probability>=0.9 &  Type=="CE"])
KCL_primary_cortical_neuron_DIV10_Tc1  <- fread("../KCL/MicroExonator/primary_cortical_neuron_DIV10_Tc1.diff", sep="\t")

Detected 11 column names but the data has 12 columns (i.e. invalid file). Added 1 extra default column name for the first column which is guessed to be row names or an index. Use setnames() afterwards if this guess is not correct, or fix the file write command that created the file to create a valid file.

KCL_primary_cortical_neuron_DIV10_Tc1  <- KCL_primary_cortical_neuron_DIV10_Tc1 [, 1:11]
colnames(KCL_primary_cortical_neuron_DIV10_Tc1 ) <- c("Gene","Node", "Coord", "Strand", "Type", "Psi_A", "Psi_B", "DeltaPsi", "Probability", "Complexity", "Entropy")
primary_cortical_neuron_DIV10_Tc1.CE.NA <- nrow(KCL_primary_cortical_neuron_DIV10_Tc1 [(abs(DeltaPsi)<0.1 | Probability<0.9)  &  Type=="CE"])
primary_cortical_neuron_DIV10_Tc1.CE.diff <- nrow(KCL_primary_cortical_neuron_DIV10_Tc1 [abs(DeltaPsi)>=0.1 & Probability>=0.9 &  Type=="CE"])
KCL_primary_cortical_neuron_DIV4_CD1  <- fread("../KCL/MicroExonator/primary_cortical_neuron_DIV4_CD1.diff", sep="\t")

Detected 11 column names but the data has 12 columns (i.e. invalid file). Added 1 extra default column name for the first column which is guessed to be row names or an index. Use setnames() afterwards if this guess is not correct, or fix the file write command that created the file to create a valid file.

KCL_primary_cortical_neuron_DIV4_CD1  <- KCL_primary_cortical_neuron_DIV4_CD1 [, 1:11]
colnames(KCL_primary_cortical_neuron_DIV4_CD1 ) <- c("Gene","Node", "Coord", "Strand", "Type", "Psi_A", "Psi_B", "DeltaPsi", "Probability", "Complexity", "Entropy")
primary_cortical_neuron_DIV4_CD1.CE.NA <- nrow(KCL_primary_cortical_neuron_DIV4_CD1 [(abs(DeltaPsi)<0.1 | Probability<0.9)  &  Type=="CE"])
primary_cortical_neuron_DIV4_CD1.CE.diff <- nrow(KCL_primary_cortical_neuron_DIV4_CD1 [abs(DeltaPsi)>=0.1 & Probability>=0.9 &  Type=="CE"])
KCL_primary_cortical_neuron_DIV10_CD1  <- fread("../KCL/MicroExonator/primary_cortical_neuron_DIV10_CD1.diff", sep="\t")

Detected 11 column names but the data has 12 columns (i.e. invalid file). Added 1 extra default column name for the first column which is guessed to be row names or an index. Use setnames() afterwards if this guess is not correct, or fix the file write command that created the file to create a valid file.

KCL_primary_cortical_neuron_DIV10_CD1  <- KCL_primary_cortical_neuron_DIV10_CD1 [, 1:11]
colnames(KCL_primary_cortical_neuron_DIV10_CD1 ) <- c("Gene","Node", "Coord", "Strand", "Type", "Psi_A", "Psi_B", "DeltaPsi", "Probability", "Complexity", "Entropy")
primary_cortical_neuron_DIV10_CD1.CE.NA <- nrow(KCL_primary_cortical_neuron_DIV10_CD1 [(abs(DeltaPsi)<0.1 | Probability<0.9)  &  Type=="CE"])
primary_cortical_neuron_DIV10_CD1.CE.diff <- nrow(KCL_primary_cortical_neuron_DIV10_CD1[abs(DeltaPsi)>=0.1 & Probability>=0.9 &  Type=="CE"])

 plot_eql_diff_binomial(
"~/Google_Drive/Results/Non_B/KCL/SS_enrichment/plus_minus/Control_vs_KCL.diff_upstream_less.bed.plus.score.All_G4.tsv.clean.txt..bed.list.out.num",
"~/Google_Drive/Results/Non_B/KCL/SS_enrichment/plus_minus/Control_vs_KCL.diff_upstream_less.bed.minus.score.All_G4.tsv.clean.txt..bed.list.out.num",
"~/Google_Drive/Results/Non_B/KCL/SS_enrichment/plus_minus/Control_vs_KCL.diff_downstream_less.bed.plus.score.All_G4.tsv.clean.txt..bed.list.out.num",
"~/Google_Drive/Results/Non_B/KCL/SS_enrichment/plus_minus/Control_vs_KCL.diff_downstream_less.bed.minus.score.All_G4.tsv.clean.txt..bed.list.out.num",
"~/Google_Drive/Results/Non_B/KCL/SS_enrichment/plus_minus/Control_vs_KCL.diff_upstream_prob_0_9.bed.plus.score.All_G4.tsv.clean.txt..bed.list.out.num",
"~/Google_Drive/Results/Non_B/KCL/SS_enrichment/plus_minus/Control_vs_KCL.diff_upstream_prob_0_9.bed.minus.score.All_G4.tsv.clean.txt..bed.list.out.num",
"~/Google_Drive/Results/Non_B/KCL/SS_enrichment/plus_minus/Control_vs_KCL.diff_downstream_prob_0_9.bed.plus.score.All_G4.tsv.clean.txt..bed.list.out.num",
"~/Google_Drive/Results/Non_B/KCL/SS_enrichment/plus_minus/Control_vs_KCL.diff_downstream_prob_0_9.bed.minus.score.All_G4.tsv.clean.txt..bed.list.out.num",
human.CE.NA,
human.CE.diff,
0.05
)

plot_eql_diff_binomial(
"~/Google_Drive/Results/Non_B/KCL/SS_enrichment/plus_minus/ESC-derived_neuron_CD1.diff_upstream_less.bed.plus.score.mm10.txt..bed.list.out.num",
"~/Google_Drive/Results/Non_B/KCL/SS_enrichment/plus_minus/ESC-derived_neuron_CD1.diff_upstream_less.bed.minus.score.mm10.txt..bed.list.out.num",
"~/Google_Drive/Results/Non_B/KCL/SS_enrichment/plus_minus/ESC-derived_neuron_CD1.diff_downstream_less.bed.plus.score.mm10.txt..bed.list.out.num",
"~/Google_Drive/Results/Non_B/KCL/SS_enrichment/plus_minus/ESC-derived_neuron_CD1.diff_downstream_less.bed.minus.score.mm10.txt..bed.list.out.num",
"~/Google_Drive/Results/Non_B/KCL/SS_enrichment/plus_minus/ESC-derived_neuron_CD1.diff_upstream_prob_0_9.bed.plus.score.mm10.txt..bed.list.out.num",
"~/Google_Drive/Results/Non_B/KCL/SS_enrichment/plus_minus/ESC-derived_neuron_CD1.diff_upstream_prob_0_9.bed.minus.score.mm10.txt..bed.list.out.num",
"~/Google_Drive/Results/Non_B/KCL/SS_enrichment/plus_minus/ESC-derived_neuron_CD1.diff_downstream_prob_0_9.bed.plus.score.mm10.txt..bed.list.out.num",
"~/Google_Drive/Results/Non_B/KCL/SS_enrichment/plus_minus/ESC-derived_neuron_CD1.diff_downstream_prob_0_9.bed.minus.score.mm10.txt..bed.list.out.num",
ESC_derived_neuron_CD1.CE.NA,
ESC_derived_neuron_CD1.CE.diff,
0.05)

plot_eql_diff_binomial(
"~/Google_Drive/Results/Non_B/KCL/SS_enrichment/plus_minus/primary_cortical_neuron_DIV10_Tc1.diff_upstream_less.bed.plus.score.mm10.txt..bed.list.out.num",
"~/Google_Drive/Results/Non_B/KCL/SS_enrichment/plus_minus/primary_cortical_neuron_DIV10_Tc1.diff_upstream_less.bed.minus.score.mm10.txt..bed.list.out.num",
"~/Google_Drive/Results/Non_B/KCL/SS_enrichment/plus_minus/primary_cortical_neuron_DIV10_Tc1.diff_downstream_less.bed.plus.score.mm10.txt..bed.list.out.num",
"~/Google_Drive/Results/Non_B/KCL/SS_enrichment/plus_minus/primary_cortical_neuron_DIV10_Tc1.diff_downstream_less.bed.minus.score.mm10.txt..bed.list.out.num",
"~/Google_Drive/Results/Non_B/KCL/SS_enrichment/plus_minus/primary_cortical_neuron_DIV10_Tc1.diff_upstream_prob_0_9.bed.plus.score.mm10.txt..bed.list.out.num",
"~/Google_Drive/Results/Non_B/KCL/SS_enrichment/plus_minus/primary_cortical_neuron_DIV10_Tc1.diff_upstream_prob_0_9.bed.minus.score.mm10.txt..bed.list.out.num",
"~/Google_Drive/Results/Non_B/KCL/SS_enrichment/plus_minus/primary_cortical_neuron_DIV10_Tc1.diff_downstream_prob_0_9.bed.plus.score.mm10.txt..bed.list.out.num",
"~/Google_Drive/Results/Non_B/KCL/SS_enrichment/plus_minus/primary_cortical_neuron_DIV10_Tc1.diff_downstream_prob_0_9.bed.minus.score.mm10.txt..bed.list.out.num",
primary_cortical_neuron_DIV10_Tc1.CE.NA,
primary_cortical_neuron_DIV10_Tc1.CE.diff,
0.05)

plot_eql_diff_binomial(
"~/Google_Drive/Results/Non_B/KCL/SS_enrichment/plus_minus/primary_cortical_neuron_DIV4_CD1.diff_upstream_less.bed.plus.score.mm10.txt..bed.list.out.num",
"~/Google_Drive/Results/Non_B/KCL/SS_enrichment/plus_minus/primary_cortical_neuron_DIV4_CD1.diff_upstream_less.bed.minus.score.mm10.txt..bed.list.out.num",
"~/Google_Drive/Results/Non_B/KCL/SS_enrichment/plus_minus/primary_cortical_neuron_DIV4_CD1.diff_downstream_less.bed.plus.score.mm10.txt..bed.list.out.num",
"~/Google_Drive/Results/Non_B/KCL/SS_enrichment/plus_minus/primary_cortical_neuron_DIV4_CD1.diff_downstream_less.bed.minus.score.mm10.txt..bed.list.out.num",
"~/Google_Drive/Results/Non_B/KCL/SS_enrichment/plus_minus/primary_cortical_neuron_DIV4_CD1.diff_upstream_prob_0_9.bed.plus.score.mm10.txt..bed.list.out.num",
"~/Google_Drive/Results/Non_B/KCL/SS_enrichment/plus_minus/primary_cortical_neuron_DIV4_CD1.diff_upstream_prob_0_9.bed.minus.score.mm10.txt..bed.list.out.num",
"~/Google_Drive/Results/Non_B/KCL/SS_enrichment/plus_minus/primary_cortical_neuron_DIV4_CD1.diff_downstream_prob_0_9.bed.plus.score.mm10.txt..bed.list.out.num",
"~/Google_Drive/Results/Non_B/KCL/SS_enrichment/plus_minus/primary_cortical_neuron_DIV4_CD1.diff_downstream_prob_0_9.bed.minus.score.mm10.txt..bed.list.out.num",
primary_cortical_neuron_DIV4_CD1.CE.NA,
primary_cortical_neuron_DIV4_CD1.CE.diff,
0.05
)

plot_eql_diff_binomial(
"~/Google_Drive/Results/Non_B/KCL/SS_enrichment/plus_minus/primary_cortical_neuron_DIV10_CD1.diff_upstream_less.bed.plus.score.mm10.txt..bed.list.out.num",
"~/Google_Drive/Results/Non_B/KCL/SS_enrichment/plus_minus/primary_cortical_neuron_DIV10_CD1.diff_upstream_less.bed.minus.score.mm10.txt..bed.list.out.num",
"~/Google_Drive/Results/Non_B/KCL/SS_enrichment/plus_minus/primary_cortical_neuron_DIV10_CD1.diff_downstream_less.bed.plus.score.mm10.txt..bed.list.out.num",
"~/Google_Drive/Results/Non_B/KCL/SS_enrichment/plus_minus/primary_cortical_neuron_DIV10_CD1.diff_downstream_less.bed.minus.score.mm10.txt..bed.list.out.num",
"~/Google_Drive/Results/Non_B/KCL/SS_enrichment/plus_minus/primary_cortical_neuron_DIV10_CD1.diff_upstream_prob_0_9.bed.plus.score.mm10.txt..bed.list.out.num",
"~/Google_Drive/Results/Non_B/KCL/SS_enrichment/plus_minus/primary_cortical_neuron_DIV10_CD1.diff_upstream_prob_0_9.bed.minus.score.mm10.txt..bed.list.out.num",
"~/Google_Drive/Results/Non_B/KCL/SS_enrichment/plus_minus/primary_cortical_neuron_DIV10_CD1.diff_downstream_prob_0_9.bed.plus.score.mm10.txt..bed.list.out.num",
"~/Google_Drive/Results/Non_B/KCL/SS_enrichment/plus_minus/primary_cortical_neuron_DIV10_CD1.diff_downstream_prob_0_9.bed.minus.score.mm10.txt..bed.list.out.num",
primary_cortical_neuron_DIV10_CD1.CE.NA,
primary_cortical_neuron_DIV10_CD1.CE.diff,
0.05)

G4seq

plot_eql_diff(
"~/Google_Drive/Results/Non_B/KCL/G4seq_enrichment/Control_vs_KCL.diff_upstream_less.bed.plus.score.GSM3003539_Homo_all_w15_th-1_plus_minus.hits.max.K.w50.25.bed.txt..bed.list.out.num",
"~/Google_Drive/Results/Non_B/KCL/G4seq_enrichment/Control_vs_KCL.diff_upstream_less.bed.minus.score.GSM3003539_Homo_all_w15_th-1_plus_minus.hits.max.K.w50.25.bed.txt..bed.list.out.num",
"~/Google_Drive/Results/Non_B/KCL/G4seq_enrichment/Control_vs_KCL.diff_downstream_less.bed.plus.score.GSM3003539_Homo_all_w15_th-1_plus_minus.hits.max.K.w50.25.bed.txt..bed.list.out.num",
"~/Google_Drive/Results/Non_B/KCL/G4seq_enrichment/Control_vs_KCL.diff_downstream_less.bed.minus.score.GSM3003539_Homo_all_w15_th-1_plus_minus.hits.max.K.w50.25.bed.txt..bed.list.out.num", 
"~/Google_Drive/Results/Non_B/KCL/G4seq_enrichment/Control_vs_KCL.diff_upstream_prob_0_9.bed.plus.score.GSM3003539_Homo_all_w15_th-1_plus_minus.hits.max.K.w50.25.bed.txt..bed.list.out.num",
"~/Google_Drive/Results/Non_B/KCL/G4seq_enrichment/Control_vs_KCL.diff_upstream_prob_0_9.bed.minus.score.GSM3003539_Homo_all_w15_th-1_plus_minus.hits.max.K.w50.25.bed.txt..bed.list.out.num",
"~/Google_Drive/Results/Non_B/KCL/G4seq_enrichment/Control_vs_KCL.diff_downstream_prob_0_9.bed.plus.score.GSM3003539_Homo_all_w15_th-1_plus_minus.hits.max.K.w50.25.bed.txt..bed.list.out.num",
"~/Google_Drive/Results/Non_B/KCL/G4seq_enrichment/Control_vs_KCL.diff_downstream_prob_0_9.bed.minus.score.GSM3003539_Homo_all_w15_th-1_plus_minus.hits.max.K.w50.25.bed.txt..bed.list.out.num"
)

Fig5.C <- plot_eql_diff_binomial(
"~/Google_Drive/Results/Non_B/KCL/G4seq_enrichment/Control_vs_KCL.diff_upstream_less.bed.plus.score.GSM3003539_Homo_all_w15_th-1_plus_minus.hits.max.K.w50.25.bed.txt..bed.list.out.num",
"~/Google_Drive/Results/Non_B/KCL/G4seq_enrichment/Control_vs_KCL.diff_upstream_less.bed.minus.score.GSM3003539_Homo_all_w15_th-1_plus_minus.hits.max.K.w50.25.bed.txt..bed.list.out.num",
"~/Google_Drive/Results/Non_B/KCL/G4seq_enrichment/Control_vs_KCL.diff_downstream_less.bed.plus.score.GSM3003539_Homo_all_w15_th-1_plus_minus.hits.max.K.w50.25.bed.txt..bed.list.out.num",
"~/Google_Drive/Results/Non_B/KCL/G4seq_enrichment/Control_vs_KCL.diff_downstream_less.bed.minus.score.GSM3003539_Homo_all_w15_th-1_plus_minus.hits.max.K.w50.25.bed.txt..bed.list.out.num", 
"~/Google_Drive/Results/Non_B/KCL/G4seq_enrichment/Control_vs_KCL.diff_upstream_prob_0_9.bed.plus.score.GSM3003539_Homo_all_w15_th-1_plus_minus.hits.max.K.w50.25.bed.txt..bed.list.out.num",
"~/Google_Drive/Results/Non_B/KCL/G4seq_enrichment/Control_vs_KCL.diff_upstream_prob_0_9.bed.minus.score.GSM3003539_Homo_all_w15_th-1_plus_minus.hits.max.K.w50.25.bed.txt..bed.list.out.num",
"~/Google_Drive/Results/Non_B/KCL/G4seq_enrichment/Control_vs_KCL.diff_downstream_prob_0_9.bed.plus.score.GSM3003539_Homo_all_w15_th-1_plus_minus.hits.max.K.w50.25.bed.txt..bed.list.out.num",
"~/Google_Drive/Results/Non_B/KCL/G4seq_enrichment/Control_vs_KCL.diff_downstream_prob_0_9.bed.minus.score.GSM3003539_Homo_all_w15_th-1_plus_minus.hits.max.K.w50.25.bed.txt..bed.list.out.num",
human.CE.NA,
human.CE.diff,
0.05)

Fig5.c <- Fig5.C +ylim( c(0.4, 2.1))
Fig5.c

Fig5.D <- plot_eql_diff_binomial(
"~/Google_Drive/Results/Non_B/KCL/G4seq_enrichment/Control_vs_KCL.diff_upstream_less.bed.plus.score.GSM3003540_Homo_all_w15_th-1_plus_minus.hits.max.PDS.w50.35.bed.txt..bed.list.out.num",
"~/Google_Drive/Results/Non_B/KCL/G4seq_enrichment/Control_vs_KCL.diff_upstream_less.bed.minus.score.GSM3003540_Homo_all_w15_th-1_plus_minus.hits.max.PDS.w50.35.bed.txt..bed.list.out.num",
"~/Google_Drive/Results/Non_B/KCL/G4seq_enrichment/Control_vs_KCL.diff_downstream_less.bed.plus.score.GSM3003540_Homo_all_w15_th-1_plus_minus.hits.max.PDS.w50.35.bed.txt..bed.list.out.num",
"~/Google_Drive/Results/Non_B/KCL/G4seq_enrichment/Control_vs_KCL.diff_downstream_less.bed.minus.score.GSM3003540_Homo_all_w15_th-1_plus_minus.hits.max.PDS.w50.35.bed.txt..bed.list.out.num",
"~/Google_Drive/Results/Non_B/KCL/G4seq_enrichment/Control_vs_KCL.diff_upstream_prob_0_9.bed.plus.score.GSM3003540_Homo_all_w15_th-1_plus_minus.hits.max.PDS.w50.35.bed.txt..bed.list.out.num",
"~/Google_Drive/Results/Non_B/KCL/G4seq_enrichment/Control_vs_KCL.diff_upstream_prob_0_9.bed.minus.score.GSM3003540_Homo_all_w15_th-1_plus_minus.hits.max.PDS.w50.35.bed.txt..bed.list.out.num",
"~/Google_Drive/Results/Non_B/KCL/G4seq_enrichment/Control_vs_KCL.diff_downstream_prob_0_9.bed.plus.score.GSM3003540_Homo_all_w15_th-1_plus_minus.hits.max.PDS.w50.35.bed.txt..bed.list.out.num",
"~/Google_Drive/Results/Non_B/KCL/G4seq_enrichment/Control_vs_KCL.diff_downstream_prob_0_9.bed.minus.score.GSM3003540_Homo_all_w15_th-1_plus_minus.hits.max.PDS.w50.35.bed.txt..bed.list.out.num",
human.CE.NA,
human.CE.diff,
0.05
)

Fig5.D <- Fig5.D +ylim( c(0.4, 2.1))
Fig5.D

sup.mus.ss_enrichment.ESC.K <- plot_eql_diff_binomial(
"~/Google_Drive/Results/Non_B/KCL/G4seq_enrichment/ESC-derived_neuron_CD1.diff_upstream_less.bed.plus.score.GSM3003547_Mouse_all_w15_th-1_plus_minus.hits.max.K.w50.25.bed.txt..bed.list.out.num",
"~/Google_Drive/Results/Non_B/KCL/G4seq_enrichment/ESC-derived_neuron_CD1.diff_upstream_less.bed.minus.score.GSM3003547_Mouse_all_w15_th-1_plus_minus.hits.max.K.w50.25.bed.txt..bed.list.out.num",
"~/Google_Drive/Results/Non_B/KCL/G4seq_enrichment/ESC-derived_neuron_CD1.diff_downstream_less.bed.plus.score.GSM3003547_Mouse_all_w15_th-1_plus_minus.hits.max.K.w50.25.bed.txt..bed.list.out.num",
"~/Google_Drive/Results/Non_B/KCL/G4seq_enrichment/ESC-derived_neuron_CD1.diff_downstream_less.bed.minus.score.GSM3003547_Mouse_all_w15_th-1_plus_minus.hits.max.K.w50.25.bed.txt..bed.list.out.num",
"~/Google_Drive/Results/Non_B/KCL/G4seq_enrichment/ESC-derived_neuron_CD1.diff_upstream_prob_0_9.bed.plus.score.GSM3003547_Mouse_all_w15_th-1_plus_minus.hits.max.K.w50.25.bed.txt..bed.list.out.num",
"~/Google_Drive/Results/Non_B/KCL/G4seq_enrichment/ESC-derived_neuron_CD1.diff_upstream_prob_0_9.bed.minus.score.GSM3003547_Mouse_all_w15_th-1_plus_minus.hits.max.K.w50.25.bed.txt..bed.list.out.num",
"~/Google_Drive/Results/Non_B/KCL/G4seq_enrichment/ESC-derived_neuron_CD1.diff_downstream_prob_0_9.bed.plus.score.GSM3003547_Mouse_all_w15_th-1_plus_minus.hits.max.K.w50.25.bed.txt..bed.list.out.num",
"~/Google_Drive/Results/Non_B/KCL/G4seq_enrichment/ESC-derived_neuron_CD1.diff_downstream_prob_0_9.bed.minus.score.GSM3003547_Mouse_all_w15_th-1_plus_minus.hits.max.K.w50.25.bed.txt..bed.list.out.num",
ESC_derived_neuron_CD1.CE.NA,
ESC_derived_neuron_CD1.CE.diff,
0.05
)

smooth

rep(1:1999, each=4)

   [1]   1   1   1   1   2   2   2   2   3   3   3   3   4   4   4   4   5   5   5   5   6   6   6   6   7   7   7   7   8   8   8   8   9   9   9   9  10  10  10  10  11  11  11  11  12  12  12
  [48]  12  13  13  13  13  14  14  14  14  15  15  15  15  16  16  16  16  17  17  17  17  18  18  18  18  19  19  19  19  20  20  20  20  21  21  21  21  22  22  22  22  23  23  23  23  24  24
  [95]  24  24  25  25  25  25  26  26  26  26  27  27  27  27  28  28  28  28  29  29  29  29  30  30  30  30  31  31  31  31  32  32  32  32  33  33  33  33  34  34  34  34  35  35  35  35  36
 [142]  36  36  36  37  37  37  37  38  38  38  38  39  39  39  39  40  40  40  40  41  41  41  41  42  42  42  42  43  43  43  43  44  44  44  44  45  45  45  45  46  46  46  46  47  47  47  47
 [189]  48  48  48  48  49  49  49  49  50  50  50  50  51  51  51  51  52  52  52  52  53  53  53  53  54  54  54  54  55  55  55  55  56  56  56  56  57  57  57  57  58  58  58  58  59  59  59
 [236]  59  60  60  60  60  61  61  61  61  62  62  62  62  63  63  63  63  64  64  64  64  65  65  65  65  66  66  66  66  67  67  67  67  68  68  68  68  69  69  69  69  70  70  70  70  71  71
 [283]  71  71  72  72  72  72  73  73  73  73  74  74  74  74  75  75  75  75  76  76  76  76  77  77  77  77  78  78  78  78  79  79  79  79  80  80  80  80  81  81  81  81  82  82  82  82  83
 [330]  83  83  83  84  84  84  84  85  85  85  85  86  86  86  86  87  87  87  87  88  88  88  88  89  89  89  89  90  90  90  90  91  91  91  91  92  92  92  92  93  93  93  93  94  94  94  94
 [377]  95  95  95  95  96  96  96  96  97  97  97  97  98  98  98  98  99  99  99  99 100 100 100 100 101 101 101 101 102 102 102 102 103 103 103 103 104 104 104 104 105 105 105 105 106 106 106
 [424] 106 107 107 107 107 108 108 108 108 109 109 109 109 110 110 110 110 111 111 111 111 112 112 112 112 113 113 113 113 114 114 114 114 115 115 115 115 116 116 116 116 117 117 117 117 118 118
 [471] 118 118 119 119 119 119 120 120 120 120 121 121 121 121 122 122 122 122 123 123 123 123 124 124 124 124 125 125 125 125 126 126 126 126 127 127 127 127 128 128 128 128 129 129 129 129 130
 [518] 130 130 130 131 131 131 131 132 132 132 132 133 133 133 133 134 134 134 134 135 135 135 135 136 136 136 136 137 137 137 137 138 138 138 138 139 139 139 139 140 140 140 140 141 141 141 141
 [565] 142 142 142 142 143 143 143 143 144 144 144 144 145 145 145 145 146 146 146 146 147 147 147 147 148 148 148 148 149 149 149 149 150 150 150 150 151 151 151 151 152 152 152 152 153 153 153
 [612] 153 154 154 154 154 155 155 155 155 156 156 156 156 157 157 157 157 158 158 158 158 159 159 159 159 160 160 160 160 161 161 161 161 162 162 162 162 163 163 163 163 164 164 164 164 165 165
 [659] 165 165 166 166 166 166 167 167 167 167 168 168 168 168 169 169 169 169 170 170 170 170 171 171 171 171 172 172 172 172 173 173 173 173 174 174 174 174 175 175 175 175 176 176 176 176 177
 [706] 177 177 177 178 178 178 178 179 179 179 179 180 180 180 180 181 181 181 181 182 182 182 182 183 183 183 183 184 184 184 184 185 185 185 185 186 186 186 186 187 187 187 187 188 188 188 188
 [753] 189 189 189 189 190 190 190 190 191 191 191 191 192 192 192 192 193 193 193 193 194 194 194 194 195 195 195 195 196 196 196 196 197 197 197 197 198 198 198 198 199 199 199 199 200 200 200
 [800] 200 201 201 201 201 202 202 202 202 203 203 203 203 204 204 204 204 205 205 205 205 206 206 206 206 207 207 207 207 208 208 208 208 209 209 209 209 210 210 210 210 211 211 211 211 212 212
 [847] 212 212 213 213 213 213 214 214 214 214 215 215 215 215 216 216 216 216 217 217 217 217 218 218 218 218 219 219 219 219 220 220 220 220 221 221 221 221 222 222 222 222 223 223 223 223 224
 [894] 224 224 224 225 225 225 225 226 226 226 226 227 227 227 227 228 228 228 228 229 229 229 229 230 230 230 230 231 231 231 231 232 232 232 232 233 233 233 233 234 234 234 234 235 235 235 235
 [941] 236 236 236 236 237 237 237 237 238 238 238 238 239 239 239 239 240 240 240 240 241 241 241 241 242 242 242 242 243 243 243 243 244 244 244 244 245 245 245 245 246 246 246 246 247 247 247
 [988] 247 248 248 248 248 249 249 249 249 250 250 250 250
 [ reached getOption("max.print") -- omitted 6996 entries ]

diff_eql.TOTAL[ , bin:=rep(1:1999, each=4) ]
diff_eql.TOTAL[, mean_Enrrichment:=mean(Enrrichment) , by=bin]
ggplot(diff_eql.TOTAL) +
  geom_line(aes(x=Position, y=mean_Enrrichment, color=type)) +
  xlim(c(-250,250)) +
  facet_grid(. ~ exon_pos  ) +
  labs(colour = "Potassium effect") +
  theme_bw() +
  theme(legend.position = "top", legend.direction = "horizontal") 

Intron lenght

ks.test(intron_size[G4>0, intron_size], intron_size[G4==0, intron_size])

p-value will be approximate in the presence of ties

    Two-sample Kolmogorov-Smirnov test

data:  intron_size[G4 > 0, intron_size] and intron_size[G4 == 0, intron_size]
D = 0.25781, p-value < 2.2e-16
alternative hypothesis: two-sided

intron_size_ints_total[ relative_frac %in% intron_size_ints_total[, max(relative_frac), by=pos]$V1, ]

   int             factor.x count.x total.x      frac.x              factor.y count.y total.y       frac.y relative_frac               pos
1:  70   int_counts_up_w_G4     150   61795 0.002427381   int_counts_up_wo_G4     509  651213 0.0007816183      3.105583   Upstream intron
2:  70 int_counts_down_w_G4     150   42311 0.003545177 int_counts_down_wo_G4     509  670697 0.0007589120      4.671395 Downstream intron

 Upstream_U2_score_len <- fread("../Figures/Figure3/Upstream_U2_score_len_matrix.txt2.old")
 Downstream_U2_score_len <- fread("../Figures/Figure3/Downstream_U2_score_len_matrix.txt2.old")
 
 
 Upstream_U2_score_len <-data.table::melt(Upstream_U2_score_len, id.vars='IL')
Downstream_U2_score_len <- data.table::melt(Downstream_U2_score_len, id.vars='IL')
Upstream_U2_score_len[, pos:="Upstream intron"]
Downstream_U2_score_len[, pos:="Downstream intron"]
 
Fig3.D1 <-  ggplot(Upstream_U2_score_len) +
   geom_tile( aes(variable, as.factor(IL), fill = value*100)) +
   scale_fill_gradient2(low="blue", high="red", mid = "grey", midpoint = 12.5, limits = c(0, 25)) +
   facet_grid(. ~ pos) +
    theme(legend.position = "bottom", legend.direction = "horizontal") + theme(axis.text.x = element_text(angle = 90)) +labs(x = NULL, y = NULL)
 
 
Fig3.D2 <-  ggplot(Downstream_U2_score_len) +
   geom_tile( aes(variable, as.factor(IL), fill = value*100)) +
   scale_fill_gradient2(low="blue", high="red", mid = "grey", midpoint = 12.5, limits = c(0, 25)) +
   facet_grid(. ~ pos) +
    theme(legend.position = "bottom", legend.direction = "horizontal") +
      theme(legend.position = "bottom", legend.direction = "horizontal") + theme(axis.text.x = element_text(angle = 90)) +labs(x = NULL, y = NULL)
Fig3.D <- plot_grid(Fig3.D1, Fig3.D2)
 Fig3.D

closest_g4 <- function(dist.exon_up_plus_path, dist.exon_up_minus_path, dist.exon_down_plus_path, dist.exon_down_minus_path){
dist.exon_up_plus <- fread(dist.exon_up_plus_path)
colnames(dist.exon_up_plus) <- c("echrom", "estart", "eend", "exon", "cero", "strand", "gchrom", "gstart", "gend", "gscore", "exon_dist")
dist.exon_up_plus[, gmid:= gstart + (gend-gstart)/2]
dist.exon_up_plus[ ,  dist:=gmid - estart]
dist.exon_up_minus <- fread(dist.exon_up_minus_path)
colnames(dist.exon_up_minus) <- c("echrom", "estart", "eend", "exon", "cero", "strand", "gchrom", "gstart", "gend", "gscore", "exon_dist")
dist.exon_up_minus[, gmid:= gstart + (gend-gstart)/2]
dist.exon_up_minus[ ,  dist:= estart - gmid]
dist.exon_down_plus <- fread(dist.exon_down_plus_path)
colnames(dist.exon_down_plus) <- c("echrom", "estart", "eend", "exon", "cero", "strand", "gchrom", "gstart", "gend", "gscore", "exon_dist")
dist.exon_down_plus[, gmid:= gstart + (gend-gstart)/2]
dist.exon_down_plus[ ,  dist:=gmid - estart]
dist.exon_down_minus <- fread(dist.exon_down_minus_path)
colnames(dist.exon_down_minus) <- c("echrom", "estart", "eend", "exon", "cero", "strand", "gchrom", "gstart", "gend", "gscore", "exon_dist")
dist.exon_down_minus[, gmid:= gstart + (gend-gstart)/2]
dist.exon_down_minus[ ,  dist:= estart - gmid]
dist.exon_up <- rbind(dist.exon_up_plus, dist.exon_up_minus) 
dist.exon_down <- rbind(dist.exon_down_plus, dist.exon_down_minus)
dist.exon_up[, pos:="3'Splice site"]
dist.exon_down[, pos:="5'Splice site"]
dist.exon <- rbind(dist.exon_up, dist.exon_down)
return(dist.exon)
}

exon.up.motif <- fread("../Figures/Figure1/exons.up.closest_G4_clean")
colnames(exon.up.motif) <- c("echrom", "estart", "eend", "exon", "cero", "strand", "gchrom", "gstart", "gend")
exon.up.motif[ , gmid:= gstart + (gend-gstart)/2]
exon.up.motif[  strand=="+"  ,  dist:=gmid - estart]
exon.up.motif[  strand=="-"  ,  dist:= estart - gmid]
exon.down.motif <- fread("../Figures/Figure1/exons.down.closest_G4_clean")
colnames(exon.down.motif) <- c("echrom", "estart", "eend", "exon", "cero", "strand", "gchrom", "gstart", "gend")
exon.down.motif[ , gmid:= gstart + (gend-gstart)/2]
exon.down.motif[  strand=="+"  ,  dist:=gmid - estart]
exon.down.motif[  strand=="-"  ,  dist:= estart - gmid]
exon.up.motif[, pos:="3'Splice site"]
exon.down.motif[, pos:="5'Splice site"]
exon.dist.motif <- rbind(exon.up.motif, exon.down.motif)
ggplot(exon.dist.motif) +
  geom_density(aes(dist)) +
  xlim(c(-1000, 1000)) +
  facet_grid(. ~ pos)

NA

closest_g4_KCL <- closest_g4("../Figures/Figure1/exon_up_plus.hg19.closest.GSM3003539_Homo_all_w15_th-1_plus_minus.hits.max.K.w50.25.bed",
                             "Figures/Figure1/exon_up_minus.hg19.closest.GSM3003539_Homo_all_w15_th-1_plus_minus.hits.max.K.w50.25.bed",
                             "Figures/Figure1/exon_down_plus.hg19.closest.GSM3003539_Homo_all_w15_th-1_plus_minus.hits.max.K.w50.25.bed",
                             "Figures/Figure1/exon_down_minus.hg19.closest.GSM3003539_Homo_all_w15_th-1_plus_minus.hits.max.K.w50.25.bed")

Error in closest_g4("../Figures/Figure1/exon_up_plus.hg19.closest.GSM3003539_Homo_all_w15_th-1_plus_minus.hits.max.K.w50.25.bed",  : 
  could not find function "closest_g4"

#closest_g4_KCL_PDS_motif


closest_g4_KCL_PDS_motif.1kb <- closest_g4_KCL_PDS_motif[abs(dist)<=1000 , ]

closest_g4_KCL_PDS_motif.1kb[, bin:=cut(dist, seq(-1000, 1000, 5), labels= seq(-995, 1000, 5), include.lowest=TRUE ) ]


closest_g4_KCL_PDS_motif.1kb.enrichment <- closest_g4_KCL_PDS_motif.1kb[ , .(Occurrences=.N) , by=c("dist", "pos", "Type")]


closest_g4_KCL_PDS_motif.1kb.enrichment.median <-  closest_g4_KCL_PDS_motif.1kb.enrichment[, .(median=median(Occurrences)), by=c( "pos", "Type") ]


closest_g4_KCL_PDS_motif.1kb.enrichment <- merge(closest_g4_KCL_PDS_motif.1kb.enrichment, closest_g4_KCL_PDS_motif.1kb.enrichment.median, by=c( "pos", "Type")) 

closest_g4_KCL_PDS_motif.1kb.enrichment[, Enrrichment:=Occurrences/median]

closest_g4_KCL_PDS_motif.1kb.enrichment[Type=="Consensus G4 motif", Type:="G4 motif" ]


#closest_g4_KCL_PDS_motif.1kb.enrichment[ , bin:=as.numeric(as.character(bin))]


ggplot(closest_g4_KCL_PDS_motif.1kb.enrichment) +
  geom_line(aes(dist, Enrrichment, colour=Type)) +
  xlim(c(-1000, 1000)) +
  facet_grid(Type ~ pos) +
  xlab("Distance") +
  ylab("Enrichment") +
  theme_bw() +
  theme(legend.position = "top", legend.direction = "horizontal")  + 
    theme(axis.text.x = element_text( angle = 45)) 

closest_g4_2015 <- function(dist.exon_up_plus_path, dist.exon_up_minus_path, dist.exon_down_plus_path, dist.exon_down_minus_path){

dist.exon_up_plus <- fread(dist.exon_up_plus_path)
colnames(dist.exon_up_plus) <- c("echrom", "estart", "eend", "exon", "cero", "strand", "gchrom", "gstart", "gend", "exon_dist")

dist.exon_up_plus[, gmid:= gstart + (gend-gstart)/2]
dist.exon_up_plus[ ,  dist:=gmid - estart]


dist.exon_up_minus <- fread(dist.exon_up_minus_path)
colnames(dist.exon_up_minus) <- c("echrom", "estart", "eend", "exon", "cero", "strand", "gchrom", "gstart", "gend",  "exon_dist")

dist.exon_up_minus[, gmid:= gstart + (gend-gstart)/2]
dist.exon_up_minus[ ,  dist:= estart - gmid]


dist.exon_down_plus <- fread(dist.exon_down_plus_path)
colnames(dist.exon_down_plus) <- c("echrom", "estart", "eend", "exon", "cero", "strand", "gchrom", "gstart", "gend",  "exon_dist")

dist.exon_down_plus[, gmid:= gstart + (gend-gstart)/2]
dist.exon_down_plus[ ,  dist:=gmid - estart]


dist.exon_down_minus <- fread(dist.exon_down_minus_path)
colnames(dist.exon_down_minus) <- c("echrom", "estart", "eend", "exon", "cero", "strand", "gchrom", "gstart", "gend",  "exon_dist")

dist.exon_down_minus[, gmid:= gstart + (gend-gstart)/2]
dist.exon_down_minus[ ,  dist:= estart - gmid]


dist.exon_up <- rbind(dist.exon_up_plus, dist.exon_up_minus) 
dist.exon_down <- rbind(dist.exon_down_plus, dist.exon_down_minus)

dist.exon_up[, pos:="3'Splice site"]
dist.exon_down[, pos:="5'Splice site"]

dist.exon <- rbind(dist.exon_up, dist.exon_down)

return(dist.exon)

}

closest_g4_KCL_2015 <- closest_g4_2015("../Figures/Figure1/exon_up_plus.hg19.closest.GSE63874_Na_K_plus_minus_hits_intersect.bed",
                             "Figures/Figure1/exon_up_minus.hg19.closest.GSE63874_Na_K_plus_minus_hits_intersect.bed",
                             "Figures/Figure1/exon_down_plus.hg19.closest.GSE63874_Na_K_plus_minus_hits_intersect.bed",
                             "Figures/Figure1/exon_down_minus.hg19.closest.GSE63874_Na_K_plus_minus_hits_intersect.bed")



closest_g4_PDS_2015 <- closest_g4_2015("../Figures/Figure1/exon_up_plus.hg19.closest.GSE63874_Na_PDS_plus_minus_hits_intersect.bed",
                             "Figures/Figure1/exon_up_minus.hg19.closest.GSE63874_Na_PDS_plus_minus_hits_intersect.bed",
                             "Figures/Figure1/exon_down_plus.hg19.closest.GSE63874_Na_PDS_plus_minus_hits_intersect.bed",
                             "Figures/Figure1/exon_down_minus.hg19.closest.GSE63874_Na_PDS_plus_minus_hits_intersect.bed")


closest_g4_KCL_2015[, Type:="G4-seq Na+ K+"]
closest_g4_PDS_2015[, Type:="G4-seq Na+ PDS"]



closest_g4_KCL_2015 <- unique(closest_g4_KCL_2015[ , c("echrom", "estart", "eend", "dist", "pos", "Type")])
closest_g4_PDS_2015 <- unique(closest_g4_PDS_2015[ , c("echrom", "estart", "eend", "dist", "pos",  "Type")])



closest_g4_KCL_PDS_2015 <- rbind(closest_g4_KCL_2015, closest_g4_PDS_2015)

ggplot(closest_g4_KCL_PDS_2015) +
  geom_line(aes(dist, colour=Type), bw=10, stat="density") +
  xlim(c(-1000, 1000)) +
  facet_grid(Type ~ pos) +
  xlab("Distance") +
  ylab("Density") +
  theme_bw() +
  theme(legend.position = "top", legend.direction = "horizontal")  + 
    theme(axis.text.x = element_text( angle = 45)) 

closest_g4_KCL.sacCer3 <- closest_g4("../Figures/Figure1/exon_up_plus.bed.sacCer3.closest.GSM3003553_Saccaromyces_all_w15_th-1_plus_minus.hits.max.K.w50.25.bed",
                             "Figures/Figure1/exon_up_minus.bed.sacCer3.closest.GSM3003553_Saccaromyces_all_w15_th-1_plus_minus.hits.max.K.w50.25.bed",
                             "Figures/Figure1/exon_down_plus.bed.sacCer3.closest.GSM3003553_Saccaromyces_all_w15_th-1_plus_minus.hits.max.K.w50.25.bed",
                             "Figures/Figure1/exon_down_minus.bed.sacCer3.closest.GSM3003553_Saccaromyces_all_w15_th-1_plus_minus.hits.max.K.w50.25.bed")

closest_g4_PDS.sacCer3 <- closest_g4("../Figures/Figure1/exon_up_plus.bed.sacCer3.closest.GSM3003554_Saccaromyces_all_w15_th-1_plus_minus.hits.max.PDS.w50.35.bed",
                             "Figures/Figure1/exon_up_minus.bed.sacCer3.closest.GSM3003554_Saccaromyces_all_w15_th-1_plus_minus.hits.max.PDS.w50.35.bed",
                             "Figures/Figure1/exon_down_plus.bed.sacCer3.closest.GSM3003554_Saccaromyces_all_w15_th-1_plus_minus.hits.max.PDS.w50.35.bed",
                             "Figures/Figure1/exon_down_minus.bed.sacCer3.closest.GSM3003554_Saccaromyces_all_w15_th-1_plus_minus.hits.max.PDS.w50.35.bed")


closest_g4_KCL.tair10 <- closest_g4("../Figures/Figure1/exon_up_plus.bed.tair10.closest.GSM3003535_Arabidopsis_all_w15_th-1_plus_minus.hits.max.K.w50.25.bed",
                             "Figures/Figure1/exon_up_minus.bed.tair10.closest.GSM3003535_Arabidopsis_all_w15_th-1_plus_minus.hits.max.K.w50.25.bed",
                             "Figures/Figure1/exon_down_plus.bed.tair10.closest.GSM3003535_Arabidopsis_all_w15_th-1_plus_minus.hits.max.K.w50.25.bed",
                             "Figures/Figure1/exon_down_minus.bed.tair10.closest.GSM3003535_Arabidopsis_all_w15_th-1_plus_minus.hits.max.K.w50.25.bed")

closest_g4_PDS.tair10 <- closest_g4("../Figures/Figure1/exon_up_plus.bed.tair10.closest.GSM3003536_Arabidopsis_all_w15_th-1_plus_minus.hits.max.PDS.w50.35.bed",
                             "Figures/Figure1/exon_up_minus.bed.tair10.closest.GSM3003536_Arabidopsis_all_w15_th-1_plus_minus.hits.max.PDS.w50.35.bed",
                             "Figures/Figure1/exon_down_plus.bed.tair10.closest.GSM3003536_Arabidopsis_all_w15_th-1_plus_minus.hits.max.PDS.w50.35.bed",
                             "Figures/Figure1/exon_down_minus.bed.tair10.closest.GSM3003536_Arabidopsis_all_w15_th-1_plus_minus.hits.max.PDS.w50.35.bed")


closest_g4_KCL.danRer10 <- closest_g4("../Figures/Figure1/exon_up_plus.danRer10.closest.GSM3003557_Zebrafish_all_w15_th-1_plus_minus.hits.max.K.w50.25.bed",
                             "Figures/Figure1/exon_up_minus.danRer10.closest.GSM3003557_Zebrafish_all_w15_th-1_plus_minus.hits.max.K.w50.25.bed",
                             "Figures/Figure1/exon_down_plus.danRer10.closest.GSM3003557_Zebrafish_all_w15_th-1_plus_minus.hits.max.K.w50.25.bed",
                             "Figures/Figure1/exon_down_minus.danRer10.closest.GSM3003557_Zebrafish_all_w15_th-1_plus_minus.hits.max.K.w50.25.bed")


closest_g4_PDS.danRer10 <- closest_g4("../Figures/Figure1/exon_up_plus.danRer10.closest.GSM3003558_Zebrafish_all_w15_th-1_plus_minus.hits.max.PDS.w50.35.bed",
                             "Figures/Figure1/exon_up_minus.danRer10.closest.GSM3003558_Zebrafish_all_w15_th-1_plus_minus.hits.max.PDS.w50.35.bed",
                             "Figures/Figure1/exon_down_plus.danRer10.closest.GSM3003558_Zebrafish_all_w15_th-1_plus_minus.hits.max.PDS.w50.35.bed",
                             "Figures/Figure1/exon_down_minus.danRer10.closest.GSM3003558_Zebrafish_all_w15_th-1_plus_minus.hits.max.PDS.w50.35.bed")


closest_g4_KCL.dm6 <- closest_g4("../Figures/Figure1/exon_up_plus.dm6.closest.GSM3003541_Drosophila_all_w15_th-1_plus_minus.hits.max.K.w50.25.bed",
                             "Figures/Figure1/exon_up_minus.dm6.closest.GSM3003541_Drosophila_all_w15_th-1_plus_minus.hits.max.K.w50.25.bed",
                             "Figures/Figure1/exon_down_plus.dm6.closest.GSM3003541_Drosophila_all_w15_th-1_plus_minus.hits.max.K.w50.25.bed",
                             "Figures/Figure1/exon_down_minus.dm6.closest.GSM3003541_Drosophila_all_w15_th-1_plus_minus.hits.max.K.w50.25.bed")


closest_g4_PDS.dm6 <- closest_g4("../Figures/Figure1/exon_up_plus.dm6.closest.GSM3003542_Drosophila_all_w15_th-1_plus_minus.hits.max.PDS.w50.35.bed",
                             "Figures/Figure1/exon_up_minus.dm6.closest.GSM3003542_Drosophila_all_w15_th-1_plus_minus.hits.max.PDS.w50.35.bed",
                             "Figures/Figure1/exon_down_plus.dm6.closest.GSM3003542_Drosophila_all_w15_th-1_plus_minus.hits.max.PDS.w50.35.bed",
                             "Figures/Figure1/exon_down_minus.dm6.closest.GSM3003542_Drosophila_all_w15_th-1_plus_minus.hits.max.PDS.w50.35.bed")


closest_g4_KCL.mm10 <- closest_g4("../Figures/Figure1/exon_up_plus.mm10.closest.GSM3003547_Mouse_all_w15_th-1_plus_minus.hits.max.K.w50.25.bed",
                             "Figures/Figure1/exon_up_minus.mm10.closest.GSM3003547_Mouse_all_w15_th-1_plus_minus.hits.max.K.w50.25.bed",
                             "Figures/Figure1/exon_down_plus.mm10.closest.GSM3003547_Mouse_all_w15_th-1_plus_minus.hits.max.K.w50.25.bed",
                             "Figures/Figure1/exon_down_minus.mm10.closest.GSM3003547_Mouse_all_w15_th-1_plus_minus.hits.max.K.w50.25.bed")

closest_g4_PDS.mm10 <- closest_g4("../Figures/Figure1/exon_up_plus.mm10.closest.GSM3003548_Mouse_all_w15_th-1_plus_minus.hits.max.PDS.w50.35.bed",
                             "Figures/Figure1/exon_up_minus.mm10.closest.GSM3003548_Mouse_all_w15_th-1_plus_minus.hits.max.PDS.w50.35.bed",
                             "Figures/Figure1/exon_down_plus.mm10.closest.GSM3003548_Mouse_all_w15_th-1_plus_minus.hits.max.PDS.w50.35.bed",
                             "Figures/Figure1/exon_down_minus.mm10.closest.GSM3003548_Mouse_all_w15_th-1_plus_minus.hits.max.PDS.w50.35.bed")


closest_g4_KCL.hg19 <- closest_g4("../Figures/Figure1/exon_up_plus.hg19.closest.GSM3003539_Homo_all_w15_th-1_plus_minus.hits.max.K.w50.25.bed",
                             "Figures/Figure1/exon_up_minus.hg19.closest.GSM3003539_Homo_all_w15_th-1_plus_minus.hits.max.K.w50.25.bed",
                             "Figures/Figure1/exon_down_plus.hg19.closest.GSM3003539_Homo_all_w15_th-1_plus_minus.hits.max.K.w50.25.bed",
                             "Figures/Figure1/exon_down_minus.hg19.closest.GSM3003539_Homo_all_w15_th-1_plus_minus.hits.max.K.w50.25.bed")

closest_g4_PDS.hg19 <- closest_g4("../Figures/Figure1/exon_up_plus.hg19.closest.GSM3003540_Homo_all_w15_th-1_plus_minus.hits.max.PDS.w50.35.bed",
                             "Figures/Figure1/exon_up_minus.hg19.closest.GSM3003540_Homo_all_w15_th-1_plus_minus.hits.max.PDS.w50.35.bed",
                             "Figures/Figure1/exon_down_plus.hg19.closest.GSM3003540_Homo_all_w15_th-1_plus_minus.hits.max.PDS.w50.35.bed",
                             "Figures/Figure1/exon_down_minus.hg19.closest.GSM3003540_Homo_all_w15_th-1_plus_minus.hits.max.PDS.w50.35.bed")



closest_g4_KCL.ce10 <- closest_g4("../Figures/Figure1/exon_up_plus.ce10.closest.GSM3003538_Celegans_all_w15_th-1_plus_minus.hits.max.PDS.w50.35.bed",
                             "Figures/Figure1/exon_up_minus.ce10.closest.GSM3003537_Celegans_all_w15_th-1_plus_minus.hits.max.K.w50.25.bed",
                             "Figures/Figure1/exon_down_plus.ce10.closest.GSM3003537_Celegans_all_w15_th-1_plus_minus.hits.max.K.w50.25.bed",
                             "Figures/Figure1/exon_down_minus.ce10.closest.GSM3003537_Celegans_all_w15_th-1_plus_minus.hits.max.K.w50.25.bed")


closest_g4_PDS.ce10 <- closest_g4("../Figures/Figure1/exon_up_plus.ce10.closest.GSM3003538_Celegans_all_w15_th-1_plus_minus.hits.max.PDS.w50.35.bed",
                             "Figures/Figure1/exon_up_minus.ce10.closest.GSM3003538_Celegans_all_w15_th-1_plus_minus.hits.max.PDS.w50.35.bed",
                             "Figures/Figure1/exon_down_plus.ce10.closest.GSM3003538_Celegans_all_w15_th-1_plus_minus.hits.max.PDS.w50.35.bed",
                             "Figures/Figure1/exon_down_minus.ce10.closest.GSM3003538_Celegans_all_w15_th-1_plus_minus.hits.max.PDS.w50.35.bed")



  


closest_g4_KCL.sacCer3[, `:=`(Treatment="KCl", Species="S. cerevisiae") ]
closest_g4_PDS.sacCer3[, `:=`(Treatment="PDS", Species="S. cerevisiae") ]
closest_g4_KCL.tair10[, `:=`(Treatment="KCl", Species="A. thaliana" ) ]
closest_g4_PDS.tair10[, `:=`(Treatment="PDS", Species="A. thaliana" ) ]
closest_g4_KCL.danRer10[, `:=`(Treatment="KCl", Species="D. rerio"  ) ]
closest_g4_PDS.danRer10[, `:=`(Treatment="PDS", Species="D. rerio"  ) ]
closest_g4_KCL.dm6[, `:=`(Treatment="KCl", Species= "D. melanogaster" ) ]
closest_g4_PDS.dm6[, `:=`(Treatment="PDS", Species=  "D. melanogaster" ) ]
closest_g4_KCL.mm10[, `:=`(Treatment="KCl", Species="M. musculus"  ) ]
closest_g4_PDS.mm10[, `:=`(Treatment="PDS", Species="M. musculus"  ) ]
closest_g4_KCL.hg19[, `:=`(Treatment="KCl", Species="H. sapiens"    ) ]
closest_g4_PDS.hg19[, `:=`(Treatment="PDS", Species="H. sapiens"    ) ]
closest_g4_KCL.ce10[, `:=`(Treatment="KCl", Species="C. elegans"    ) ]
closest_g4_PDS.ce10[, `:=`(Treatment="PDS", Species="C. elegans"   ) ]


closest_g4.TOTAL <- rbind(closest_g4_KCL.sacCer3,
closest_g4_PDS.sacCer3,
closest_g4_KCL.tair10,
closest_g4_PDS.tair10,
closest_g4_KCL.danRer10,
closest_g4_PDS.danRer10,
closest_g4_KCL.dm6,
closest_g4_PDS.dm6,
closest_g4_KCL.mm10,
closest_g4_PDS.mm10,
closest_g4_KCL.hg19,
closest_g4_PDS.hg19,
closest_g4_KCL.hg19,
closest_g4_PDS.hg19)


ggplot(closest_g4.TOTAL) +
  geom_line(aes(dist, colour=Species), bw=10, stat="density") +
  xlim(c(-1000, 1000)) +
  facet_grid(Treatment ~ pos) +
  xlab("Distance") +
  ylab("Density") +
  theme_bw() +
  theme(legend.position = "top", legend.direction = "horizontal")  + 
  theme(axis.text.x = element_text(vjust = 0.7, 
    angle = 45)) 

closest_g4.TOTAL.1kb <- closest_g4.TOTAL[abs(dist)<=1000 , ]

Error: object 'closest_g4.TOTAL' not found

read_dist_table_plus_minus <- function(path.plus, path.minus ){
  
dist_table.plus <- data.table(read_delim(path.plus, 
    "\t", escape_double = FALSE, col_names = FALSE, 
    trim_ws = TRUE))
dist_table.plus <- dist_table.plus[, 2:2001]
dist_table.plus <- data.table(as.data.frame(t(dist_table.plus)))
colnames(dist_table.plus) <- c("Position", "Occurrences")
dist_table.minus <- data.table(read_delim(path.minus, 
    "\t", escape_double = FALSE, col_names = FALSE, 
    trim_ws = TRUE))
dist_table.minus <- dist_table.minus[, 2:2001]
dist_table.minus <- data.table(as.data.frame(t(dist_table.minus)))
colnames(dist_table.minus) <- c("Position", "Occurrences")
 
dist_table <-  merge(dist_table.plus, dist_table.minus, by="Position")
dist_table[, Occurrences:=(Occurrences.x + Occurrences.y)]
dist_table[, Occurrences:=(Occurrences.x + Occurrences.y)]
dist_table <- dist_table[, c("Position", "Occurrences")]
dist_table[,median:=median(Occurrences)]
dist_table[, Enrrichment:=Occurrences/median]
dist_table[, Position:=Position-1]
return(dist_table)  
}

enrichment_G4_seq_plot <- function(path.up_plus.plus, path.up_plus.minus, 
                                   path.down_plus.plus, path.down_plus.minus, 
                                   path.up_minus.plus, path.up_minus.minus,
                                   path.down_minus.plus, path.down_minus.minus ){
x.up_plus <- read_dist_table_plus_minus(path.up_plus.plus,
                           path.up_plus.minus)
x.down_plus <- read_dist_table_plus_minus(path.down_plus.plus,
                           path.down_plus.minus)
x.up_minus <- read_dist_table_plus_minus(path.up_minus.plus,
                           path.up_minus.minus)
x.down_minus <- read_dist_table_plus_minus(path.down_minus.plus,
                          path.down_minus.minus)
x.up_minus[,Position:=Position*-1]
x.down_minus[,Position:=Position*-1]
x.TOTAL <- plot_density(x.up_plus, x.up_minus, x.down_plus, x.down_minus)
return(x.TOTAL)
}

hg19.TOTAL.KCL <- enrichment_G4_seq_plot("./G4_seq_2019/Evolution/exon_up_plus.hg19.score.GSM3003539_Homo_all_w15_th-1_plus.hits.max.K.w50.25.bed.txt..num",
                       "./G4_seq_2019/Evolution/exon_up_plus.hg19.score.GSM3003539_Homo_all_w15_th-1_minus.hits.max.K.w50.25.bed.txt..num",
                       "./G4_seq_2019/Evolution/exon_down_plus.hg19.score.GSM3003539_Homo_all_w15_th-1_plus.hits.max.K.w50.25.bed.txt..num",
                       "./G4_seq_2019/Evolution/exon_down_plus.hg19.score.GSM3003539_Homo_all_w15_th-1_minus.hits.max.K.w50.25.bed.txt..num",
                       "./G4_seq_2019/Evolution/exon_up_minus.hg19.score.GSM3003539_Homo_all_w15_th-1_plus.hits.max.K.w50.25.bed.txt..num",
                       "./G4_seq_2019/Evolution/exon_up_minus.hg19.score.GSM3003539_Homo_all_w15_th-1_minus.hits.max.K.w50.25.bed.txt..num",
                       "./G4_seq_2019/Evolution/exon_down_minus.hg19.score.GSM3003539_Homo_all_w15_th-1_plus.hits.max.K.w50.25.bed.txt..num",
                       "./G4_seq_2019/Evolution/exon_down_minus.hg19.score.GSM3003539_Homo_all_w15_th-1_minus.hits.max.K.w50.25.bed.txt..num")

Error in read_dist_table_plus_minus(path.up_plus.plus, path.up_plus.minus) : 
  could not find function "read_dist_table_plus_minus"

hg19.TOTAL.KCL[, Treatment:="KCl"] 
hg19.TOTAL.PDS[, Treatment:="PDS"]
hg19.TOTAL.KCL[, Species:="H. sapiens"] 
hg19.TOTAL.PDS[, Species:="H. sapiens"]  

sacCer3.TOTAL.KCL[, Treatment:="KCl"]  
sacCer3.TOTAL.PDS[, Treatment:="PDS"]
sacCer3.TOTAL.KCL[, Species:="S. cerevisiae"]  
sacCer3.TOTAL.PDS[, Species:="S. cerevisiae"]  

mouse.TOTAL.KCL[, Treatment:="KCl"]  
mouse.TOTAL.PDS[, Treatment:="PDS"] 
mouse.TOTAL.KCL[, Species:="M. musculus"]  
mouse.TOTAL.PDS[, Species:="M. musculus"]  

dm6.TOTAL.KCL[, Treatment:="KCl"]  
dm6.TOTAL.PDS[, Treatment:="PDS"]
dm6.TOTAL.KCL[, Species:="D. melanogaster"]  
dm6.TOTAL.PDS[, Species:="D. melanogaster"]  

tair10.TOTAL.KCL[, Treatment:="KCl"] 
tair10.TOTAL.PDS[, Treatment:="PDS"] 
tair10.TOTAL.KCL[, Species:="A. thaliana"] 
tair10.TOTAL.PDS[, Species:="A. thaliana"] 

danRer10.TOTAL.KCL[, Treatment:="KCl"]  
danRer10.TOTAL.PDS[, Treatment:="PDS"]
danRer10.TOTAL.KCL[, Species:="D. rerio"]  
danRer10.TOTAL.PDS[, Species:="D. rerio"]


TOTAL.KCL_PDS <-  rbind(hg19.TOTAL.KCL, hg19.TOTAL.PDS, sacCer3.TOTAL.KCL, sacCer3.TOTAL.PDS, mouse.TOTAL.KCL, mouse.TOTAL.PDS, dm6.TOTAL.KCL, dm6.TOTAL.PDS, tair10.TOTAL.KCL, tair10.TOTAL.PDS, danRer10.TOTAL.KCL, danRer10.TOTAL.PDS)


ggplot(TOTAL.KCL_PDS) +
  geom_line(aes(Position, Enrrichment, colour=Species)) +
  xlim(c(-1000, 1000)) +
  facet_grid(Treatment ~ exon_pos) +
  xlab("Distance") +
  ylab("Enrichment") +
  theme_bw() +
  theme(legend.position = "top", legend.direction = "horizontal")  + 
  theme(axis.text.x = element_text(vjust = 0.7, 
    angle = 45)) 

closest_g4_KCL.hg19.2015 <- closest_g4("../Figures/Supplementary/exon_up_plus.hg19.closest.GSE63874_Na_K_plus_minus_hits_intersect.bed",
                             "Figures/Supplementary/exon_up_minus.hg19.closest.GSE63874_Na_K_plus_minus_hits_intersect.bed",
                             "Figures/Supplementary/exon_down_plus.hg19.closest.GSE63874_Na_K_plus_minus_hits_intersect.bed",
                             "Figures/Supplementary/exon_down_minus.hg19.closest.GSE63874_Na_K_plus_minus_hits_intersect.bed")

Error in closest_g4("../Figures/Supplementary/exon_up_plus.hg19.closest.GSE63874_Na_K_plus_minus_hits_intersect.bed",  : 
  could not find function "closest_g4"

KCL_up <- unique(closest_g4_KCL[abs(dist)>=100 & pos=="3'Splice site", paste(echrom, estart, eend, sep = "_")])

gg_color_hue <- function(n) {
  hues = seq(15, 375, length = n + 1)
  hcl(h = hues, l = 65, c = 100)[1:n]
}
gg_color_hue(3)

[1] "#F8766D" "#00BA38" "#619CFF"

 library(eulerr)

package ‘eulerr’ was built under R version 3.5.2

VennDiag.up_2015 <- euler(c("Motif" = 18132,  
                    "K" = 34761,  
                    "PDS" = 50894, 
                    "K&PDS" = 31711,
                    "PDS&Motif" = 14786,
                    "K&Motif" = 11794,
                    "K&PDS&Motif" = 11250))
venn_supp.up <- plot(VennDiag.up_2015, counts = TRUE, font=2, cex=1, alpha=0.5,
     fill=gg_color_hue(3), quantities = list(fontsize = 10))
VennDiag.down_2015 <- euler(c("Motif" = 19649,  
                    "K" = 33908,  
                    "PDS" = 49806, 
                    "K&PDS" = 30920,
                    "PDS&Motif" = 15951,
                    "K&Motif" = 12615,
                    "K&PDS&Motif" = 12027))
venn_supp.down <- plot(VennDiag.down_2015, counts = TRUE, font=1, cex=1, alpha=0.5,
     fill=gg_color_hue(3),  quantities = list(fontsize = 10))
plot_grid(venn_supp.up, venn_supp.down, labels = c("3' Splice site", "5' Splice site"))

dataframe_G4_consensus_motif_enrichment_species <- fread("../Figures/Figure1/dataframe_G4_consensus_motif_enrichment_species")

dataframe_G4_consensus_motif_enrichment_species_matrix <- t(dataframe_G4_consensus_motif_enrichment_species)



header <- as.character(head(dataframe_G4_consensus_motif_enrichment_species_matrix, 1))

dataframe_G4_consensus_motif_enrichment_species_df <- as.data.frame(tail(dataframe_G4_consensus_motif_enrichment_species_matrix, -1))

colnames(dataframe_G4_consensus_motif_enrichment_species_df) <- header

dataframe_G4_consensus_motif_enrichment_species_df$specie <- rownames(dataframe_G4_consensus_motif_enrichment_species_df)


dataframe_G4_consensus_motif_enrichment_species_dt <- data.table(dataframe_G4_consensus_motif_enrichment_species_df)

dataframe_G4_consensus_motif_enrichment_species_dt$median <- as.numeric(as.character(dataframe_G4_consensus_motif_enrichment_species_dt$median))
dataframe_G4_consensus_motif_enrichment_species_dt$st.dev <- as.numeric(as.character(dataframe_G4_consensus_motif_enrichment_species_dt$st.dev))

dataframe_G4_consensus_motif_enrichment_species_dt$specie <- factor(dataframe_G4_consensus_motif_enrichment_species_dt$specie , levels=dataframe_G4_consensus_motif_enrichment_species_dt[order(-median)]$specie)

Fig6.A <- ggplot(dataframe_G4_consensus_motif_enrichment_species_dt, aes(x = specie, y=median) ) +
  geom_bar( stat="identity", colour="black", fill="white") +
  geom_errorbar(aes(ymin = (median - st.dev), ymax = (as.numeric(median) + as.numeric(st.dev))), colour="red" , width=0.2) +
  theme_bw()+
  xlab("Species") +
  ylab("Density (G4s / kB)") +
  theme(axis.text.x = element_text(vjust = 0.7, 
    angle = 45))

Fig6.A

dataframe_evo_PDS_K <- fread("../Figures/Figure1/dataframe_evo_PDS_K")




dataframe_evo_PDS_K_matrix <- t(dataframe_evo_PDS_K)



header <- as.character(head(dataframe_evo_PDS_K_matrix, 1))

dataframe_evo_PDS_K_df <- as.data.frame(tail(dataframe_evo_PDS_K_matrix, -1))

colnames(dataframe_evo_PDS_K_df) <- header


dataframe_evo_PDS_K_df$Species <- rownames(dataframe_evo_PDS_K_df)

dataframe_evo_PDS_K_dt <- data.table(dataframe_evo_PDS_K_df)

dataframe_evo_PDS_K_dt_nice <- rbind(dataframe_evo_PDS_K_dt[ , .(Species=Species, Treatment="K+", median=K_median, st.dev=K_st.dev  )  ],
dataframe_evo_PDS_K_dt[ , .(Species=Species, Treatment="PDS", median=PDS_median, st.dev=PDS_st.dev  )  ])


dataframe_evo_PDS_K_dt_nice$median <- as.numeric(as.character(dataframe_evo_PDS_K_dt_nice$median))
dataframe_evo_PDS_K_dt_nice$st.dev <- as.numeric(as.character(dataframe_evo_PDS_K_dt_nice$st.dev))


ggplot(dataframe_evo_PDS_K_dt_nice, aes(x = Species, y=median, group=Treatment)) +
  geom_bar( aes(colour=Treatment ), stat="identity", fill="white", position="dodge") +
  geom_errorbar(aes(ymin = (median - st.dev), ymax = (as.numeric(median) + as.numeric(st.dev))), colour="black" , width=0.2,  position = position_dodge()) +
  theme_bw()+
  xlab("Species") +
  ylab("Density (G4s / kB)") +
  theme(axis.text.x = element_text(vjust = 0.7, 
    angle = 45))



dataframe_evo_PDS_K_dt_nice$Species <- factor(dataframe_evo_PDS_K_dt_nice$Species , levels=dataframe_evo_PDS_K_dt_nice[Treatment=="PDS"][order(-median)]$Species)


Fig6.C <-  ggplot(dataframe_evo_PDS_K_dt_nice, aes(x=Species, weight=median, ymin=median-st.dev, ymax=median+st.dev, group=Treatment)) +
     geom_bar(position=position_dodge(), aes(y=median, color=Treatment), fill="white", stat="identity") +
     geom_errorbar (position=position_dodge(width=0.9), colour="black", width=0.2) +
    theme_bw()+
  xlab("Species") +
  ylab("Density (G4s / kB)") +
  theme(axis.text.x = element_text(vjust = 0.7, 
    angle = 45))


Fig6.C

dataframe_evo_PDS_K_dt_nice

Figures

Fig1.BC <- plot_grid(Fig1.B, Fig1.C, ncol=1, labels = c("B", "C"), rel_heights = c(2, 1))

Error in plot_grid(Fig1.B, Fig1.C, ncol = 1, labels = c("B", "C"), rel_heights = c(2,  : 
  object 'Fig1.B' not found

Fig2 <- plot_grid(Fig2.A, Fig2.B,ncol = 1 , labels ="AUTO", rel_heights = c(1.5, 1))
Fig2

Fig5.bottom <- plot_grid(Fig5.A, Fig5.B, Fig5.C, Fig5.D, nrow = 2, ncol = 2 , labels = c("B", "C", "D", "E"), rel_heights = c(1, 1, 1, 1))

Removed 2996 rows containing missing values (geom_path).Removed 2996 rows containing missing values (geom_path).

Fig5 <- plot_grid(Fig5.A1, Fig5.bottom, nrow=2, labels = c("A", ""),  rel_heights = c(2, 4))
Fig5

Fig6.top <- plot_grid(Fig6.A, Fig6.C, labels = c("A", "C"))
Fig6.bottom <- plot_grid(Fig6.B, Fig6.D, labels = c("B", "D"))

Fig6 <- plot_grid(Fig6.A, Fig6.C, Fig6.B , Fig6.D, labels = c("A", "C", "B", "D") , ncol=2, rel_heights = c(1, 1, 3, 3))


Fig6 <- plot_grid(Fig6.top, Fig6.bottom, rel_heights = c(1, 1.5), nrow=2)
Fig6